CN116208970B - Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception - Google Patents

Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception Download PDF

Info

Publication number
CN116208970B
CN116208970B CN202310408910.2A CN202310408910A CN116208970B CN 116208970 B CN116208970 B CN 116208970B CN 202310408910 A CN202310408910 A CN 202310408910A CN 116208970 B CN116208970 B CN 116208970B
Authority
CN
China
Prior art keywords
representing
node
user
edge
content
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310408910.2A
Other languages
Chinese (zh)
Other versions
CN116208970A (en
Inventor
陈赓
周玉祥
郭银景
曾庆田
张煜东
孙红雨
陆翔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University of Science and Technology
Original Assignee
Shandong University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong University of Science and Technology filed Critical Shandong University of Science and Technology
Priority to CN202310408910.2A priority Critical patent/CN116208970B/en
Publication of CN116208970A publication Critical patent/CN116208970A/en
Application granted granted Critical
Publication of CN116208970B publication Critical patent/CN116208970B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Abstract

The invention discloses a space-ground cooperation unloading and content acquisition method based on knowledge-graph perception, which belongs to the technical field of mobile communication and comprises the following steps: in the urban environment with the lower edge covered by the 5G macro base station, constructing a hollow cooperative unloading and content acquisition model of an on-board self-organizing network environment; dynamically arranging and constructing an edge service knowledge graph based on edge node attributes and a plurality of time-varying parameter knowledge relations among nodes; establishing a system utility function weighted by multiple performance indexes; and constructing space-ground collaborative unloading and content acquisition optimal strategies based on edge service knowledge graph perception for different types of user demands by adopting a theoretical optimization and clipping near-end strategy optimization algorithm. The invention solves the problems of space-ground collaboration unloading and content acquisition of users with different service demands in the vehicle-mounted self-organizing network in the edge urban environment, reduces the edge service delay and lease utility expenditure while maximizing arrangement and utilization of the edge idle resources, and improves the service quality demands of the edge users.

Description

Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception
Technical Field
The invention belongs to the technical field of mobile communication, and particularly relates to a space-ground collaboration unloading and content acquisition method based on knowledge-graph sensing.
Background
With the development and popularity of intelligent terminals, a number of delay-sensitive and computation-intensive applications, such as face recognition, natural language processing, real-time streaming media, and virtual/augmented reality, are emerging, which present new challenges for edge computing offloading. In order to fully explore the influence of time-varying parameters among edge devices on the service quality of users in edge service and maximize arrangement and utilization of edge idle resources, task unloading and content acquisition strategies are made for different types of users with different requirements in time, and the method has important significance for research on space-ground collaborative unloading and content acquisition based on knowledge-graph perception in a vehicle-mounted self-organizing network.
In recent years, knowledge-centric edge computing architectures have become a research hotspot due to the ability to perceive user-dependent tasks, network structures, or edge-limited resources. However, the high-speed mobility of the vehicles and the increase of the registration number lead to the occurrence of fluctuation and idling of edge resources, the influence of complex logic parameters among heterogeneous edge devices on the edge unloading of the dependent tasks cannot be reflected at the same time, and a large amount of idle resources among the vehicles can not be fully arranged and utilized when a single edge service node is selected for unloading along with the exponential increase of the number of the vehicles on the road. Therefore, how to arrange and construct the dynamic knowledge relationship of the edge service knowledge graph is a key problem of the research of the invention, and meanwhile, the discovery and sharing virtualization of the edge adjacent resources of the Internet of vehicles are of great research value.
The research significance and research value of dynamic arrangement of multi-time-varying parameter logic knowledge relation between edge environments and discovery sharing of edge adjacent resources are comprehensively improved, and a space-to-ground collaborative unloading and content acquisition method based on knowledge graph perception is needed to better optimize task unloading and content acquisition of edge users and improve service quality experience of the edge users.
Disclosure of Invention
In order to solve the problems, the invention provides an air-ground collaboration unloading and content acquisition method based on knowledge graph perception, which aims at the dependence task unloading requirements and the different content acquisition requirements of different types of users, and solves the problems of air-ground collaboration unloading and content acquisition of different types of users in the vehicle-mounted self-organizing network edge city environment by taking into consideration the dynamic arrangement of a plurality of time-varying parameter knowledge between vehicle edge environment equipment, the perception deployment of air edge nodes and the establishment of a vehicle virtual shared resource pool in the edge nodes and the users.
The technical scheme of the invention is as follows:
a space-ground collaboration unloading and content acquisition method based on knowledge-graph perception comprises the following steps: step 1, constructing an edge vehicle-mounted self-organizing network environment hollow cooperative unloading and content acquisition model consisting of a macro base station, remote cloud, non-preset track aerial edge nodes, road mobile vehicles and two types of mobile users with different types and different requirements in a 5G macro base station coverage lower edge urban environment; step 2, dynamically arranging and constructing an edge service knowledge graph based on edge node attributes and a plurality of time-varying parameter knowledge relations among nodes; step 3, analyzing user service quality influence factors under different service strategies and establishing a multi-performance index weighted system utility function according to node perception deployment and a vehicle-mounted self-organizing network shared resource pooling knowledge model; and 4, constructing an air-ground collaborative unloading and content acquisition optimal strategy based on edge service knowledge graph perception for different types of user demands by adopting a theoretical optimization and clipping near-end strategy optimization algorithm.
Further, in the step 1, an edge city air-ground cooperation scene of a 5G macro base station covering remote cloud, an air edge node, road moving vehicles and two types of mobile users with different types and different requirements is considered; the macro base station is provided with an edge knowledge server for knowledge spectrum sensing, senses physical entity information of users, vehicles and aerial edge nodes in a coverage area, is connected with a remote cloud in an optical fiber communication mode, and contains a large amount of computing resources and cache content fragment sets; meanwhile, quantitatively labeling the positions of different physical entities in the scene by establishing a three-dimensional coordinate system; the unmanned aerial vehicle with fixed height flies at a non-preset angle to be used as an air edge node for flexible perception decision deployment, a minimum safety distance is set between adjacent air edge nodes, and the air edge node contains computing resources and part of the existing cache content set updated periodically so as to assist a user to carry out task unloading, relay forwarding and cache content providing, wherein the air edge node and a macro base station communicate through an air link; two kinds of task users with different moving speeds and tolerant time delays exist in the scene, namely a common user and a vehicle-mounted user; a plurality of moving vehicle nodes exist on the surrounding roads of the cell, each vehicle node carries a virtual machine capable of carrying out logic resource migration and an existing cache content fragment set of the vehicle node which is updated periodically, and the virtual machine has vehicle residual computing resources with heterogeneous different sizes and trust dependence social attributes between users and the vehicle nodes; a small number of non-trusted vehicles exist, the vehicles are divided into a host vehicle and auxiliary shared vehicles sharing resources in the edge service process, communication availability ranges exist among different vehicle nodes and among vehicle nodes and task users, and the users communicate with the aerial edge nodes, the vehicle nodes and the host vehicle and the auxiliary shared vehicles through wireless communication links; the air edge node and the vehicle node also serve as edge cache nodes to provide content for users with content acquisition requirements.
Further, in step 2, the specific process of constructing the edge service knowledge graph is as follows: step 2.1, abstracting the air-ground collaboration unloading and content acquisition model network entity constructed in the step 1 into nodes and establishing different logic layers, namely a program task layer, a user layer, a vehicle node layer, an air edge node layer and a cloud node layer; step 2.2, extracting and analyzing characteristic knowledge of nodes in each layer, and extracting multi-time-varying parameter knowledge relations among the nodes in the layers; step 2.3, node attribute embedding is carried out on the intra-layer nodes, time-varying parameter knowledge relation arrangement among the nodes is carried out to construct edge relations and parameter weight factors, and multi-time-varying parameter relation arrangement is carried out on the inter-layer nodes according to different edge relation criteria to construct inter-layer node knowledge relations and parameter weight factors; step 2.4, establishing an undirected weighted graph to obtain an edge service knowledge graph; the method comprises the following steps: for multiple times by different side relation criteriaDynamic arrangement of variable parameter knowledge relationship, obtaining edge service knowledge graph, and representing the edge service knowledge graph as undirected weighted graph
Figure SMS_1
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
Figure SMS_2
Representing node set,/->
Figure SMS_3
Representing edges in the undirected weighted graph, +.>
Figure SMS_4
Representing the embedded parametric weight.
Further, in step 3, the specific procedure for establishing the system utility function weighted by the multiple performance indexes is as follows: step 3.1, constructing an air-ground communication model: the method comprises the following steps: step 3.1.1, calculating the transmission rate of the space-to-ground communication model by using a shannon formula, and respectively calculating the uplink transmission rate and the downlink transmission rate between nodes during space-to-ground communication as follows:
Figure SMS_5
(1)；
Figure SMS_6
(2)；
Wherein, during uplink communication, the node
Figure SMS_8
As transmitting node, node->
Figure SMS_10
As receiving node->
Figure SMS_12
Representing nodes
Figure SMS_13
To node->
Figure SMS_14
Uplink transmission rate of space-to-ground communication, +.>
Figure SMS_15
Representing node->
Figure SMS_16
To node->
Figure SMS_17
Bandwidth resources allocated for upstream communication between, < >>
Figure SMS_18
Representing node->
Figure SMS_19
Is set to the transmission power of (a); node ∈during downlink communication>
Figure SMS_20
As transmitting node, node->
Figure SMS_21
As receiving node->
Figure SMS_23
Representing node->
Figure SMS_25
To node->
Figure SMS_26
Downlink transmission rate of space-to-ground communication, +.>
Figure SMS_7
Representing node->
Figure SMS_9
To node->
Figure SMS_11
Bandwidth resources allocated for downstream communication between +.>
Figure SMS_22
Representing node->
Figure SMS_24
Is set to the transmission power of (a); />
Figure SMS_27
An additive white gaussian noise representing the time of space communication; />
Figure SMS_28
Representing node->
Figure SMS_29
And node->
Figure SMS_30
Path loss factor between->
Figure SMS_31
The calculation formula is as follows:
Figure SMS_32
(3)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_34
representing the carrier frequency +.>
Figure SMS_37
Indicating the speed of light +.>
Figure SMS_38
Representing node->
Figure SMS_39
And node->
Figure SMS_40
The distance between the two plates is set to be equal,
Figure SMS_41
representing node->
Figure SMS_42
And node->
Figure SMS_33
Probability of line-of-sight links between +.>
Figure SMS_35
And->
Figure SMS_36
Respectively representing the environmental loss of the line-of-sight link and the non-line-of-sight link; step 3.1.2, calculating the transmission rate of the ground communication model by a shannon formula; the communication transmission rate between the user and the vehicle node virtual edge is calculated as follows:
Figure SMS_43
(4)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_60
Representing ground emission node->
Figure SMS_61
And ground receiving node->
Figure SMS_64
The uplink transmission rate between the two,
Figure SMS_66
representing ground emission node->
Figure SMS_68
And ground receiving node->
Figure SMS_69
Bandwidth resources allocated between, ">
Figure SMS_72
Representing ground emission node->
Figure SMS_74
Transmit power of>
Figure SMS_76
Indicating channel gain, +.>
Figure SMS_77
Representing ground emission node->
Figure SMS_79
And ground receiving node->
Figure SMS_81
Distance between->
Figure SMS_83
An additive white gaussian noise representing when a user communicates with a virtual edge of a vehicle node and between vehicle nodes; step 3.2, constructing a task model; the method comprises the following steps: based on the full duplex communication technology, the user can simultaneously perform space-ground collaborative task unloading and content acquisition, and the requirements of the user are divided into calculation unloading requirements and content acquisition requirements; exist under each time slot
Figure SMS_84
Individual users and each user generates only one application +.>
Figure SMS_85
Application->
Figure SMS_44
Can be divided into->
Figure SMS_53
A subtask with a dependency relationship, defined as an attribute tuple +.>
Figure SMS_55
The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_58
representing user +.>
Figure SMS_59
Type of->
Figure SMS_62
Representing transmission dataSize of->
Figure SMS_63
Representing the required calculation amount +.>
Figure SMS_65
Representing the maximum tolerated delay +.>
Figure SMS_67
Representing subtask dependency properties,>
Figure SMS_70
representing a subtask sequence number; in terms of user content acquisition request, there is +. >
Figure SMS_71
The individual demand users, the demand users are all users +.>
Figure SMS_73
In (2) generating a content acquisition request per user while generating a computation offload request, will +.>
Figure SMS_75
The individual demand user acquisition request is defined as
Figure SMS_78
Wherein->
Figure SMS_80
Representing the user of the demand +.>
Figure SMS_82
Size of requested content->
Figure SMS_45
Representing the user of the demand +.>
Figure SMS_46
Obtaining the preference degree of the content->
Figure SMS_47
Cable representing content segmentsGuide (S)/(S)>
Figure SMS_48
Representing the user of the demand +.>
Figure SMS_49
Obtaining the maximum tolerable time delay of the content; step 3.3, constructing a calculation model; the method comprises the following steps: by the variable->
Figure SMS_50
、
Figure SMS_51
、/>
Figure SMS_52
、/>
Figure SMS_54
The method comprises the steps of respectively representing four task unloading modes of a user, an aerial edge node, vehicle virtual resource sharing and remote cloud, wherein each subtask can only select one unloading mode; step 3.3.1, user self unloading mode: subtask->
Figure SMS_56
Completion delay of offloading at user node itself +.>
Figure SMS_57
Expressed as:
Figure SMS_86
(5)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_87
representing user +.>
Figure SMS_89
Subtask->
Figure SMS_90
The amount of calculation required +.>
Figure SMS_91
Representing user +.>
Figure SMS_92
Is a computing resource of (a); meanwhile, the user uninstalls the leasing resources without leasing the computing resources, and the leasing utility of the computing resources is 0; step 3.3.2, aerial edge node unloading mode: subtask->
Figure SMS_93
Offloading to an over-the-air edge node->
Figure SMS_94
Is->
Figure SMS_88
Expressed as:
Figure SMS_95
(6)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_111
Representing the total number of edge nodes over the air, +.>
Figure SMS_112
Representation and air edge node->
Figure SMS_113
Is used to determine the correlation factor of (a),
Figure SMS_114
representing user +.>
Figure SMS_115
Subtask->
Figure SMS_116
Transmission data size, +.>
Figure SMS_117
Representing the user +.>
Figure SMS_96
Subtasks of->
Figure SMS_98
Uplink transmission to an over-the-air edge node->
Figure SMS_100
Transmission rate of>
Figure SMS_101
Representing user +.>
Figure SMS_104
Subtask->
Figure SMS_106
The amount of calculation required +.>
Figure SMS_107
Representing the air edge node +.>
Figure SMS_108
Assigned to user->
Figure SMS_97
Neutron task->
Figure SMS_99
Is proportional to the computing resource of->
Figure SMS_102
Representing the air edge node +.>
Figure SMS_103
Is a residual computing resource of (1); user->
Figure SMS_105
Subtask->
Figure SMS_109
Leasing utility generated by leasing air edge node computing resources>
Figure SMS_110
Expressed as:
Figure SMS_118
(7)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_119
representing lease price of computing resources of the aerial edge node; step 3.3.3, sharing and unloading mode of virtual resources of the vehicle: in addition to considering different idle resources of vehicles, social trust relationship between users and a vehicle-mounted self-organizing network is considered, and user nodes can sense and comprehensively infer candidate host vehicles and auxiliary shared vehicles through a knowledge graph, dynamically arrange virtual logic resources on virtual machines to construct a stable shared virtual resource pool, and the pool computing resources are shared>
Figure SMS_120
Expressed as:
Figure SMS_121
(8)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_123
representing user and mobile vehicle node->
Figure SMS_124
Trust between dependent on social properties->
Figure SMS_126
Representing a mobile vehicle node +. >
Figure SMS_128
Left computing resources of->
Figure SMS_129
Factor indicating whether it is an auxiliary shared vehicle, +.>
Figure SMS_130
Representing auxiliary shared vehicle->
Figure SMS_131
Trust dependent social attributes, +.>
Figure SMS_122
Representing auxiliary shared vehicle->
Figure SMS_125
Is a computing resource of (a); task completion delay for offloading subtasks to vehicle virtual resource sharing +.>
Figure SMS_127
Expressed as:
Figure SMS_132
(9)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_136
representing user +.>
Figure SMS_137
Type of->
Figure SMS_138
Representing the total number of nodes of the mobile vehicle, +.>
Figure SMS_139
Factor indicating whether or not it is a candidate host vehicle +.>
Figure SMS_140
Representing user +.>
Figure SMS_141
Subtasks of->
Figure SMS_142
Uplink to mobile vehicle node->
Figure SMS_133
Transmission rate of>
Figure SMS_143
Representing user +.>
Figure SMS_144
Subtask->
Figure SMS_145
Transmission data size, +.>
Figure SMS_146
Representing user +.>
Figure SMS_147
Subtask->
Figure SMS_148
The amount of calculation required; user->
Figure SMS_149
Subtask->
Figure SMS_134
Rental utility generated by rental vehicle virtual computing resources>
Figure SMS_135
Expressed as:
Figure SMS_150
(10)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_151
representing a vehicle node computing resource lease price; step 3.3.4, remote cloud node unloading mode: the cloud can process a plurality of subtasks simultaneously, and the completion time delay of the subtasks to be unloaded to a remote cloud node is +.>
Figure SMS_152
The method comprises the following steps:
Figure SMS_153
(11)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_159
representing air edge nodes and users->
Figure SMS_160
Cover factor of->
Figure SMS_161
Indicating the size of the data to be transmitted,
Figure SMS_162
representing ∈k from the air edge node>
Figure SMS_163
Uplink transmission rate to base station, +.>
Figure SMS_164
Representing user +.>
Figure SMS_165
Subtask- >
Figure SMS_154
Uplink transmission rate to base station, +.>
Figure SMS_156
Indicating uplink transmission rate between base station and cloud, < >>
Figure SMS_157
Representing cloud allocation to users->
Figure SMS_158
Subtask->
Figure SMS_166
Is proportional to the computing resource of->
Figure SMS_167
Representing remaining computing resources of the remote cloud node; user->
Figure SMS_168
Subtasks
Figure SMS_169
Leasing utility generated by leasing remote cloud computing resources>
Figure SMS_155
Expressed as:
Figure SMS_170
(12)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_172
representing time slot->
Figure SMS_173
Calculating the lease price of the resource by the remote cloud node; step 3.4, constructing a content acquisition model; the method comprises the following steps: the presence of content acquisition requirements where part of the users may have different access preferences while taking user task offloading into account, content requirement mobile users can choose to acquire preferred content from vehicle nodes, air edge nodes and remote cloud nodes, let ∈ ->
Figure SMS_174
、/>
Figure SMS_175
、/>
Figure SMS_176
Three different acquisition modes of a vehicle node, an air edge node and a remote cloud node are respectively represented; step 3.4.1, vehicle node acquisition mode: demand user->
Figure SMS_177
From the mobile vehicle node->
Figure SMS_178
Completion delay of acquiring content>
Figure SMS_171
Expressed as:
Figure SMS_179
(13)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_180
representing the user of the demand +.>
Figure SMS_181
Size of requested content->
Figure SMS_182
Representing the user of the demand +.>
Figure SMS_183
And mobile vehicle node->
Figure SMS_184
Downlink transmission rate between the two; rental utility of requiring a user to download vehicle node content>
Figure SMS_185
Expressed as:
Figure SMS_186
(14)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_187
rental price indicating that the demand user obtains the desired content from the vehicle node,/->
Figure SMS_188
Representing the user of the demand +.>
Figure SMS_189
Acquiring the preference degree of the content; step 3.4.2, air edge node acquisition mode: demand user->
Figure SMS_190
From the air edge node->
Figure SMS_191
Completion delay of acquiring content>
Figure SMS_192
Expressed as:
Figure SMS_193
(15)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_194
representing the user's need for content retrieval>
Figure SMS_195
And air edge node->
Figure SMS_196
Is used to determine the correlation factor of (a),
Figure SMS_197
representing the air edge node +.>
Figure SMS_198
Is +.>
Figure SMS_199
Downlink transmission rate between the two; rental utility of requiring users to download over-the-air edge node content>
Figure SMS_200
Expressed as:
Figure SMS_201
(16)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_202
representing lease unit price for requiring a user to acquire content from an aerial edge node; step 3.4.3, remote cloud node acquisition mode: demand user->
Figure SMS_203
Completion delay of obtaining content from remote cloud node +.>
Figure SMS_204
Expressed as:
Figure SMS_205
(17)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_206
and->
Figure SMS_207
Representing cloud node to base station and base station to demand user +.>
Figure SMS_208
Is a downlink transmission rate of (a); demand user->
Figure SMS_209
Rental utility of downloading remote cloud node content +.>
Figure SMS_210
Expressed as:
Figure SMS_211
(18)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_212
representing time slot->
Figure SMS_213
Requiring the user to acquire the lease price of the content from the remote node; step 3.5, establishing a system utility function weighted by multiple performance indexes; the specific process is as follows: step 3.5.1, by taking into account the different possible offloading modes, slot +. >
Figure SMS_214
Delay and +.>
Figure SMS_215
Expressed as:
Figure SMS_216
(19)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_218
representing subtasks->
Figure SMS_219
Dependency of attribute factor->
Figure SMS_221
Is->
Figure SMS_223
Dependency variable value at attribute time, +.>
Figure SMS_225
Representing the total amount of subtask dependent properties +.>
Figure SMS_227
Representing user +.>
Figure SMS_229
Subtask->
Figure SMS_231
Selecting self-unloading->
Figure SMS_233
Representing subtasks->
Figure SMS_235
Delay in the completion of the self-offloading of the user node +.>
Figure SMS_237
Representing user +.>
Figure SMS_238
Subtask->
Figure SMS_239
Selecting over-the-air edge node offload,>
Figure SMS_240
representing subtasks->
Figure SMS_241
Offloading to an over-the-air edge node->
Figure SMS_217
Completion delay of->
Figure SMS_220
Representing user +.>
Figure SMS_222
Subtask->
Figure SMS_224
Selecting vehicle virtual resource sharing offload, +.>
Figure SMS_226
Task completion latency representing offloading of subtasks to vehicle virtual resource sharing +.>
Figure SMS_228
Representing user +.>
Figure SMS_230
Subtask->
Figure SMS_232
Selecting remote cloud for task offloading, +.>
Figure SMS_234
Representing the completion time delay of the subtask offloading to the remote cloud node; step 3.5.2, leasing computing resource leasing utility generated by edge node>
Figure SMS_236
Expressed as:
Figure SMS_242
(20)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_244
representing user +.>
Figure SMS_246
Subtask->
Figure SMS_248
Leasing the air edge node computing resource generated leasing utility,
Figure SMS_249
representing user +.>
Figure SMS_251
Subtask->
Figure SMS_252
Rental utility generated by rental vehicle virtual computing resources, +.>
Figure SMS_253
Representing a user
Figure SMS_243
Subtask->
Figure SMS_245
Leasing the leasing utility generated by the remote cloud computing resource; step 3.5.3, combining different content acquisition strategies, requiring the user to be in slot +. >
Figure SMS_247
Content acquisition delay and->
Figure SMS_250
Expressed as:
Figure SMS_254
(21)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_255
representing the user of the demand +.>
Figure SMS_256
Selecting a vehicle node content acquisition mode,/->
Figure SMS_257
Representing the user of the demand +.>
Figure SMS_258
Selecting an over-the-air edge node content acquisition mode, +.>
Figure SMS_259
Representing the user of the demand +.>
Figure SMS_260
Selecting a remote cloud node content acquisition mode; step 3.5.4, service rental utility of user-acquired edge node content associated with user demand content size and popularity ∈>
Figure SMS_261
Expressed as:
Figure SMS_262
(22)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_263
rental utility indicating that the user is required to download the contents of the vehicle node,/->
Figure SMS_264
Rental utility indicating that the user is required to download the content of the edge node in air,/->
Figure SMS_265
Representing leasing utility of a demand user to download remote cloud node content; step 3.5.5, quantitatively analyzing and calculating a system utility function represented by a weighted sum of unloading and content acquisition time delay, and the expense lease utility of user lease edge resources and content acquisition service expense lease utility->
Figure SMS_266
：
Figure SMS_267
(23)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_269
、/>
Figure SMS_271
、/>
Figure SMS_273
、/>
Figure SMS_275
respectively represent time slots->
Figure SMS_276
Delay and +.>
Figure SMS_278
Computing resource lease utility generated by lease edge node>
Figure SMS_279
The demand user is in time slot->
Figure SMS_268
Content acquisition delay and->
Figure SMS_270
Service rental utility of user obtaining edge node content>
Figure SMS_272
Weight coefficient of>
Figure SMS_274
、/>
Figure SMS_277
Representing computing resource lease utility and acquisition edges, respectively The edge node content service leases a discount factor for utility.
Further, in step 4, the specific process of obtaining the optimal strategy is as follows: step 4.1, constructing an optimization problem; the method comprises the following steps: minimizing computing unloading delay, content acquisition delay of edge service, leasing edge computing resources by users and leasing edge content utility expenditure and achieving the goal of maximizing long-term network utility; definition of the definition
Figure SMS_287
Represents the maximum number of time slots,/->
Figure SMS_288
Representing a non-preset angle; />
Figure SMS_289
Representing user +.>
Figure SMS_290
Subtasks of->
Figure SMS_291
Selecting a user self, an air edge node, vehicle virtual resource sharing and remote cloud node computing unloading mode and requiring users +.>
Figure SMS_292
Selecting three content acquisition modes of a vehicle node, an aerial edge node and a remote cloud node; />
Figure SMS_297
Indicating that a user can only select one mode to perform task unloading and content acquisition; />
Figure SMS_281
Subtask representing user->
Figure SMS_282
When different computing task unloading is selected, only one air edge node and one vehicle node are selected as a host vehicle, and a user is required to be +.>
Figure SMS_284
When content acquisition is carried out through the aerial edge node, only one node is selected; />
Figure SMS_285
Indicating that the distance between the air edge nodes is not less than the minimum safe distance, and the non-preset angle change range is +. >
Figure SMS_293
；/>
Figure SMS_294
Indicating that the mobile positions of the air edge node, the vehicle node and the user do not exceed the set area limit; />
Figure SMS_295
A scale factor representing the allocation of computing resources; />
Figure SMS_296
And
Figure SMS_280
indicating that the distribution of computing resources does not exceed the total computing resources of the user node, the air edge node and the remote cloud node during unloading respectively; />
Figure SMS_283
Indicating that the task calculation unloading time delay does not exceed the maximum unloading tolerance time delay, and the user content request time delay is smaller than or equal to the maximum unloading tolerance time delay of the content request; the original optimization problem established is expressed as +.>
Figure SMS_286
：
Figure SMS_298
(24)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_311
representing the user's need for content retrieval>
Figure SMS_313
And air edge node->
Figure SMS_316
Is a correlation factor of (2); />
Figure SMS_318
Representing the air edge node +.>
Figure SMS_320
And another air edge node->
Figure SMS_321
A distance therebetween; />
Figure SMS_322
Representing a minimum security distance between adjacent air edge nodes; />
Figure SMS_323
Representing the air edge node +.>
Figure SMS_324
Is a horizontal axis coordinate value; />
Figure SMS_326
Representing user +.>
Figure SMS_328
Is a horizontal axis coordinate value;
Figure SMS_330
representing a mobile vehicle node +.>
Figure SMS_333
Is a horizontal axis coordinate value; />
Figure SMS_334
A horizontal axis coordinate value representing the coverage area boundary of the macro base station;
Figure SMS_335
representing the air edge node +.>
Figure SMS_299
Is a vertical axis coordinate value of (2); />
Figure SMS_302
Representing user +.>
Figure SMS_304
Is a vertical axis coordinate value of (2); />
Figure SMS_306
Representing a mobile vehicle node +.>
Figure SMS_308
Is a vertical axis coordinate value of (2); />
Figure SMS_310
Representing the vertical axis coordinate value of the coverage area boundary of the macro base station; / >
Figure SMS_312
Representing user +.>
Figure SMS_314
Subtasks of->
Figure SMS_315
Is used for unloading calculation time delay; />
Figure SMS_317
Representing user +.>
Figure SMS_319
Subtasks of->
Figure SMS_325
Unloading the maximum tolerant delay; />
Figure SMS_327
Representing a demand user
Figure SMS_329
Selecting content acquisition time delay generated by adding different content acquisition modes; />
Figure SMS_331
Representing the user of the demand +.>
Figure SMS_332
Maximum tolerant time delay of content acquisition; step 4.2, optimizing the solution: first, the original optimization problem->
Figure SMS_300
The medium discrete variable is relaxed to be changed into a continuous interval variable; second, introducing an upper-bound relaxation variable to the maximum nonlinear term in the objective function>
Figure SMS_301
Converting it into linear term while adding new constraint +.>
Figure SMS_303
Optimization problem after relaxation->
Figure SMS_305
Is->
Figure SMS_307
Performing an equivalent solution; the optimization problem is expressed as follows after simplification>
Figure SMS_309
：
Figure SMS_336
(25)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_341
representing user +.>
Figure SMS_342
Subtasks of->
Figure SMS_343
Selecting leasing utilities of computing resources generated by adding different unloading modes; />Representing the user of the demand +.>
Figure SMS_345
Selecting content acquisition time delay generated by adding different content acquisition modes; />
Figure SMS_346
Representing the user of the demand +.>
Figure SMS_347
Selecting a content service lease utility generated by adding different content acquisitions; />
Figure SMS_337
Represents a relaxation of four unloading and three content acquisition discrete variables into a continuous variable between 0 and 1,/v>
Figure SMS_348
Representing the user +. >
Figure SMS_349
The dependency attribute factor in all subtasks is +.>
Figure SMS_350
Upper bound relaxation variable constraint of ∈10->
Figure SMS_351
Representing subtasks->
Figure SMS_352
Dependency of attribute factor->
Figure SMS_353
Is->
Figure SMS_354
Dependency variable value at attribute time, +.>
Figure SMS_338
Representing user +.>
Figure SMS_339
The dependency attribute factor in all subtasks is +.>
Figure SMS_340
Upper limit relaxation variable of (2);
the optimization problem is decomposed into three sub-problems by a block coordinate descent method and a successive approximation algorithm: user computing offload and content acquisition variable sub-questions
Figure SMS_355
Sub-problem of calculating the resource allocation proportion variable ≡>
Figure SMS_356
And the sub-problem of deployment angle variable of the air node->
Figure SMS_357
The method comprises the steps of carrying out a first treatment on the surface of the The decomposition of a specific sub-problem is represented as follows: step 4.2.1, giving a non-preset angle and calculating a resource allocation proportion strategy, and solving an unloading and content acquisition strategy; />
Figure SMS_358
(26)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_359
a discount factor representing the utility of a lease of a computing resource, +.>
Figure SMS_360
Representing a discount factor for obtaining the lease utility of the edge node content service; step 4.2.2, given task unloading, content acquisition and non-preset angle strategies, solving a calculation resource allocation proportion strategy; because no variable coupling relation exists between the distribution of the computing resources and the acquisition of the content, the optimization problem is further simplified to obtain the sub-problem +.>Still belonging to the same solution problem;
Figure SMS_362
(27)；
step 4.2.3, giving task unloading, content acquisition and calculating a resource allocation proportion strategy, and solving an optimal track strategy of the aerial edge node; optimization problem with respect to post relaxation
Figure SMS_363
And variable influence analysis, further simplifying the problem into sub-problems with the same solution when solving the trajectory optimization strategy>
Figure SMS_364
；
Figure SMS_365
(28)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_367
representing a non-preset angle +.>
Figure SMS_368
In the range of 0 to->
Figure SMS_369
Between (I)>
Figure SMS_370
Representing the air edge node +.>
Figure SMS_371
And another air edge node->
Figure SMS_372
Distance between->
Figure SMS_373
Not lower than the minimum safe distance; finally, by giving a part of optimized variable parameters, carrying out variable relaxation by combining Taylor expansion of local points, solving different sub-problems after converting a non-convex optimization problem into a convex optimization problem, and comparing multiple iterations with a set threshold value to obtain the optimizationTheoretical optimal boundary solution of the problem; step 4.3, optimizing and perceiving decision analysis under deployment and shared resource pooling based on continuous clipping near-end strategies: first, the initial network state of the system is defined as +.>
Figure SMS_366
：/>
Figure SMS_374
(29)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_392
representing user +.>
Figure SMS_394
Is (are) moved positions>
Figure SMS_397
Representing user +.>
Figure SMS_399
Is>
Figure SMS_401
Representing user +.>
Figure SMS_403
Transition probability of->
Figure SMS_405
Representing user +.>
Figure SMS_406
Is->
Figure SMS_407
Representing the user of the demand +.>
Figure SMS_408
Is (are) acquired request>
Figure SMS_409
Representing user +.>
Figure SMS_410
Task model with task topology knowledge relationship, +.>
Figure SMS_411
Representing a mobile vehicle node +.>
Figure SMS_412
Is (are) located>
Figure SMS_413
Representing a mobile vehicle node +.>
Figure SMS_375
Is>
Figure SMS_377
Representing a mobile vehicle node +. >
Figure SMS_379
Trust dependent social attributes, +.>
Figure SMS_381
Representing a mobile vehicle node +.>
Figure SMS_383
Left computing resources of->
Figure SMS_385
Representing a mobile vehicle node +.>
Figure SMS_387
Existing cached content piece set,/->
Figure SMS_389
Represent the first
Figure SMS_391
Post-deployment location of individual air edge nodes, +.>
Figure SMS_393
Representing the speed of movement of the edge node in air, +.>
Figure SMS_395
Representing the air edge node +.>
Figure SMS_396
Left computing resources of->
Figure SMS_398
Representing the air edge node +.>
Figure SMS_400
Part of the existing cached content set,/->
Figure SMS_402
Indicating macro base station coordinate position,/->
Figure SMS_404
Representing remaining computing resources of remote cloud node, +.>
Figure SMS_376
Representing a cached content segment set in the cloud; analyzing a plurality of knowledge factors influencing the quality of service performance, arranging the dynamic knowledge relationship to construct an edge service knowledge graph, and obtaining preprocessing knowledge state information expressed as +.>
Figure SMS_378
The method comprises the steps of carrying out a first treatment on the surface of the Second, define the complex motion space under each time slot as +.>
Figure SMS_380
Wherein, the method comprises the steps of, wherein,
Figure SMS_382
representing user +.>
Figure SMS_384
Subtasks of->
Figure SMS_386
Different offloading policies of->
Figure SMS_388
Representing different content acquisition strategies of a demand user; the set bonus function under each time slot is denoted +.>
Figure SMS_390
。
Further, in step 4.3, the overall flow of space-to-ground collaborative offloading and content acquisition under perceived deployment and shared resource pooling optimized based on continuous clipping near-end policy is as follows: step 4.3.1, constructing an air-ground collaboration unloading and content acquisition model composed of remote cloud, non-preset track air edge nodes, road mobile vehicles and two types of mobile users with different types and different requirements, and initializing parameters; step 4.3.2, executing a training round, and initializing a training model to obtain an initial state; step 4.3.3, executing time slot rounds, analyzing a plurality of time-varying parameter relation arrangement of nodes in layers and among layers to construct an edge service knowledge graph, and obtaining knowledge state information; step 4.3.4, the knowledge server selects an action strategy through a strategy network; step 4.3.5, the action strategy is put into the environment for execution, and rewards under the current network state, the next network state, the system utility function, the unloading and content acquisition strategy and the stored experience tuples are obtained; step 4.3.6, judging whether the parameters of the current strategy network need to be updated, if so, entering another strategy network and evaluating the network to carry out training update, otherwise, continuously executing and updating the network state; 4.3.7, if all time slot training is finished, calculating average network rewards, finishing one training round, and initializing a training model; and 4.3.8, if the training round is finished, obtaining an average network reward and an optimal service strategy, and outputting the space cooperation unloading and content acquisition scheme as an optimal scheme.
The beneficial technical effects brought by the invention are as follows: according to the invention, a 5G macro base station is considered to cover a remote cloud, an aerial edge node, a mobile vehicle and a vehicle-mounted self-organizing network edge urban space-ground cooperation environment with concurrent different types of user demands, an edge service knowledge graph is dynamically arranged and constructed based on edge node attributes and a plurality of time-varying parameter knowledge relations among the nodes, a system utility function weighted by multiple performance indexes in four edge unloading modes and three content acquisition modes is established according to edge node perception deployment and a vehicle-mounted self-organizing network virtual resource sharing pooling knowledge model, and a space-ground cooperation unloading and content acquisition strategy based on edge service knowledge graph perception is constructed for the different types of user demands by using a theoretical optimization and cutting near-end strategy optimization algorithm. The invention solves the problems of space-to-ground collaborative unloading and content acquisition of different types of users in the vehicle-mounted self-organizing network edge city environment by taking into consideration the dynamic arrangement of a plurality of time-varying parameter knowledge between the vehicle edge environment equipment, the perceived deployment of the aerial edge nodes and the method for establishing the vehicle virtual shared resource pool in the edge nodes and the users from the angles of the dependency task unloading requirements and the different content acquisition requirements of different types of users, thereby effectively reducing the edge service delay and the lease utility and improving the service quality requirements of the edge users while maximally arranging and utilizing the edge idle resources.
Drawings
Fig. 1 is a schematic block diagram of a space-ground collaboration unloading and content acquisition method based on knowledge-graph perception.
Fig. 2 is a schematic diagram of a space-ground collaboration unloading and content acquisition model based on knowledge-graph perception.
FIG. 3 is a schematic diagram of an edge service knowledge aware layer model according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the attached drawings and detailed description:
as shown in fig. 1, a space-ground collaboration unloading and content obtaining method based on knowledge-graph perception comprises the following steps:
step 1, constructing an edge vehicle-mounted self-organizing network environment hollow cooperative unloading and content acquisition model consisting of a macro base station, a remote cloud, a non-preset track aerial edge node, a road mobile vehicle and two types of mobile users with different types and different requirements in a 5G macro base station coverage lower edge urban environment. The invention considers the edge city of the 5G macro base station covering remote cloud, air edge node, road mobile vehicle and two kinds of mobile users with different types and different demandsThe space-city collaboration scenario is shown in fig. 2. The macro base station is provided with an edge knowledge server for knowledge spectrum sensing, can sense physical entity information of users, vehicles and aerial edge nodes in a coverage area, is connected with a remote cloud in an optical fiber communication mode, and contains a large amount of computing resources and cache content fragment sets
Figure SMS_414
In the present embodiment
Figure SMS_416
，/>
Figure SMS_418
Indicate->
Figure SMS_420
Content piece->
Figure SMS_422
Representing the total number of content segments. Meanwhile, quantitatively marking the positions of different physical entities in the scene by establishing a three-dimensional coordinate system, and expressing the coordinate positions of the macro base station as
Figure SMS_425
。/>
Figure SMS_427
Unmanned aerial vehicle of a fixed height (+)>
Figure SMS_429
The unmanned plane is->
Figure SMS_431
An air edge node, thus use->
Figure SMS_433
Representing the total number of edge nodes in air) at a non-preset angle +.>
Figure SMS_436
Flexible perceptive decision deployment of flights as airborne edge nodesFirst->
Figure SMS_437
The position of each air edge node after deployment is +.>
Figure SMS_439
The minimum security distance between adjacent air edge nodes is +.>
Figure SMS_441
Partial existing cache content set containing computing resources and periodic updates in air edge node +.>
Figure SMS_442
To assist the requesting user in task offloading, relay forwarding and providing cached content, in this embodiment +.>
Figure SMS_415
The air edge node communicates with the macro base station via an air link. Two kinds of task users with different moving speeds and tolerant time delays exist in the scene, namely a common user and a vehicle-mounted user, and the users are +.>
Figure SMS_417
The position is expressed as +.>
Figure SMS_419
. Co-existence of +.>
Figure SMS_421
Vehicle moving vehicle, moving vehicle node +.>
Figure SMS_423
The position of (2) is expressed as +.>
Figure SMS_424
Mobile vehicle node +. >
Figure SMS_426
Is expressed as +.>Each vehicle carries a virtual machine capable of logical resource migration and a periodically updated mobile vehicle node +.>
Figure SMS_430
Existing cached content fragment set->
Figure SMS_432
Mobile vehicle nodes with heterogeneous and different sizes in virtual machine +.>
Figure SMS_434
Is->
Figure SMS_435
User and mobile vehicle node->
Figure SMS_438
Trust-dependent social properties between->
Figure SMS_440
There are a small number of non-trusted vehicles and auxiliary shared vehicles in which the vehicles are to be divided into a host vehicle and shared resources during edge service, there is a range of availability of communication between different vehicle nodes, between vehicle nodes and task users, and communication between the users and air edge nodes, between the vehicle nodes and the host vehicle and auxiliary shared vehicles is performed by wireless communication links. The air edge node and the vehicle node also serve as edge cache nodes to provide content for users with content acquisition requirements.
In the invention, the weighting of the task calculation unloading time delay, the content acquisition time delay, the lease computing resource expense utility and the lease edge content expense utility is used for representing the system utility function. The invention has the core problems of how to synthesize the multi-time-varying parameter dynamic knowledge relationship among the edge devices to construct the edge service knowledge graph and acquire the optimal edge service strategy of the demand user so as to effectively reduce the edge service time delay and lease utility expenditure and improve the service quality demand of the edge user.
And 2, dynamically arranging and constructing an edge service knowledge graph based on the edge node attribute and a plurality of time-varying parameter knowledge relations among the nodes. An edge service knowledge perception layer model schematic diagram established by abstracting and synthesizing a plurality of time-varying parameter logic knowledge is shown in fig. 3, wherein an edge logic layer in the knowledge perception layer model comprises a program task layer, a user layer, a vehicle node layer, an air edge node layer and a cloud node layer. In the air edge node layer, each air edge node analyzes a distance parameter relation with adjacent air nodes to establish an intra-layer knowledge link for information transfer; in the user layer, an intra-layer knowledge link is established between the vehicle-mounted user node and the common user node by analyzing the inter-node distance parameter relation to carry out information transfer; in a vehicle node layer, establishing an intra-layer knowledge link between a main vehicle node, an untrusted vehicle node and an auxiliary shared vehicle node by analyzing a social trust relationship, a relative moving speed, connection availability and other time-varying parameter relationships to carry out information transfer, so that vehicle virtual resource sharing is formed, and the intra-layer knowledge link between the untrusted vehicle node and the auxiliary shared vehicle node which is unavailable in connection availability cannot be established; analyzing the dependency relationship between the user node application subtasks and different subtasks in the program task layer to establish an intra-layer knowledge link; and performing task mapping between the user layer and the program task layer, and performing virtual resource migration mapping between the vehicle node layer and the virtual resource pool. The user layer can establish an uplink unloading interlayer logic selection strategy, and the user layer, the cloud node layer, the air edge layer and the vehicle node layer can respectively establish the uplink unloading interlayer logic selection strategy and the downlink content acquisition interlayer logic selection strategy. The knowledge server can collect the perception information of different edge logic layers and perceive the related information such as edge nodes, users, idle resources, application program task files and the like in the coverage area. The specific process is as follows:
Step 2.1, abstracting the air-ground collaboration unloading and content acquisition model network entity constructed in the step 1 into nodes and establishing different logic layers, namely abstracting different network entities in an edge city environment to obtain different logic layers, namely a program task layer, a user layer, a vehicle node layer, an air edge node layer and a cloud node layer;
step 2.2, extracting and analyzing node characteristic knowledge in each layer, and simultaneously extracting multi-time-varying parameter knowledge relations among the layer nodes, namely extracting user abstract node positions, moving speeds, transition probabilities, program task mapping relations and content request knowledge characteristics, and simultaneously extracting edge attribute knowledge characteristics such as content caching, idle resources, moving speeds, connection availability, social attribute trust relations and the like of the edge nodes;
step 2.3, node attribute embedding is carried out on the intra-layer nodes, time-varying parameter knowledge relation arrangement among the nodes is carried out to construct edge relations and parameter weight factors, and multi-time-varying parameter relation arrangement is carried out on the inter-layer nodes according to different edge relation criteria to construct inter-layer node knowledge relations and parameter weight factors;
step 2.4, establishing an undirected weighted graph to obtain an edge service knowledge graph; the method comprises the following steps: the edge service knowledge graph is obtained through dynamic arrangement of different side relation criteria on multi-time-varying parameter knowledge relations and is expressed as an undirected weighted graph
Figure SMS_443
. Wherein (1)>
Figure SMS_444
Representing node set,/->
Figure SMS_445
Representing edges in the undirected weighted graph, +.>
Figure SMS_446
Representing the embedded parametric weight. The same different nodes can cache the content required by the user, and the user content acquisition requirement can be better served through the establishment of time-varying parameter logic knowledge.
And step 3, analyzing the influence factors of the user service quality under different service strategies and establishing a multi-performance index weighted system utility function. The specific process is as follows:
step 3.1, constructing an air-ground communication model; the method comprises the following steps: step 3.1.1, calculating the transmission rate of the space-to-ground communication model by using a shannon formula, and respectively calculating the uplink transmission rate and the downlink transmission rate between nodes during space-to-ground communication as follows:
Figure SMS_447
(1)；
Figure SMS_448
(2)；
wherein, during uplink communication, the node
Figure SMS_450
As transmitting node, node->
Figure SMS_451
As receiving node->
Figure SMS_452
Representing nodes
Figure SMS_453
To node->
Figure SMS_455
Uplink transmission rate of space-to-ground communication, +.>
Figure SMS_456
Representing node->
Figure SMS_457
To node->
Figure SMS_458
Bandwidth resources allocated for upstream communication between, < >>
Figure SMS_462
Representing node->
Figure SMS_465
Is set to the transmission power of (a); node ∈during downlink communication>
Figure SMS_466
As transmitting node, node->
Figure SMS_468
As receiving node->
Figure SMS_470
Representing node->
Figure SMS_472
To node->
Figure SMS_473
Downlink transmission rate of space-to-ground communication, +.>
Figure SMS_449
Representing node->
Figure SMS_454
To node- >
Figure SMS_459
Bandwidth resources allocated for downstream communication between +.>
Figure SMS_460
Representing node->
Figure SMS_461
Is set to the transmission power of (a); />
Figure SMS_463
An additive white gaussian noise representing the time of space communication; />
Figure SMS_464
Representing node->
Figure SMS_467
And node->
Figure SMS_469
Path loss factor between->
Figure SMS_471
The calculation formula is as follows:
Figure SMS_474
(3)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_476
representing the carrier frequency +.>
Figure SMS_477
Indicating the speed of light +.>
Figure SMS_479
Representing node->
Figure SMS_481
And node->
Figure SMS_482
The distance between the two plates is set to be equal,
Figure SMS_483
representing node->
Figure SMS_484
And node->
Figure SMS_475
Probability of line-of-sight links between +.>
Figure SMS_478
And->
Figure SMS_480
The environmental loss of the line-of-sight link and the non-line-of-sight link are represented, respectively.
Step 3.1.2, calculating the transmission rate of the ground communication model by a shannon formula; the communication transmission rate between the user and the vehicle node virtual edge communication and the vehicle node can be calculated as:
Figure SMS_485
(4)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_487
representing ground emission node->
Figure SMS_488
And ground receiving node->
Figure SMS_490
The uplink transmission rate between the two,
Figure SMS_492
representing ground emission node->
Figure SMS_494
And ground receiving node->
Figure SMS_496
Bandwidth resources allocated between, ">
Figure SMS_498
Representing ground emission node->
Figure SMS_486
Transmit power of>
Figure SMS_489
Indicating channel gain, +.>
Figure SMS_491
Representing ground emission node->
Figure SMS_493
And ground receiving node->
Figure SMS_495
Distance between->
Figure SMS_497
Representing additive white gaussian noise when a user communicates with a virtual edge of a vehicle node and between vehicle nodes.
Step 3.2, constructing a task model; the method comprises the following steps: based on full duplex communication technology, users can simultaneously perform space-ground collaborative task unloading and content acquisition, and the method is to be used The demands of the user are divided into computational offload demands and content acquisition demands. Exist under each time slot
Figure SMS_500
Individual users and each user generates only one application +.>
Figure SMS_501
Application->
Figure SMS_503
Can be divided into->
Figure SMS_504
A subtask with a dependency relationship, defined as an attribute tuple +.>
Figure SMS_505
. Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_508
representing user +.>
Figure SMS_510
Type of->
Figure SMS_512
Representing the size of the transmitted data +.>
Figure SMS_514
Representing the required calculation amount +.>
Figure SMS_516
Representing the maximum tolerated delay +.>
Figure SMS_517
Representing subtask dependency properties,>
Figure SMS_519
representing the subtask sequence number. In terms of user content acquisition request, there is +.>
Figure SMS_520
Individual demand users (demandThe user is all users->
Figure SMS_521
Some of the users in (a), each user generates a content acquisition request while generating a computation offload request, will +.>
Figure SMS_522
The individual demand user acquisition request is defined as
Figure SMS_499
Wherein->
Figure SMS_502
Representing the user of the demand +.>
Figure SMS_506
Size of requested content->
Figure SMS_507
Representing the user of the demand +.>
Figure SMS_509
Obtaining the preference degree of the content->
Figure SMS_511
Index representing content piece (i.e.)>
Figure SMS_513
Content piece), ->
Figure SMS_515
Representing the user of the demand +.>
Figure SMS_518
The maximum tolerable delay of the content is obtained.
Step 3.3, constructing a calculation model; the method comprises the following steps: by variable amounts
Figure SMS_523
、/>
Figure SMS_524
、/>
Figure SMS_525
、
Figure SMS_526
The method respectively represents four task unloading modes of a user, an aerial edge node, vehicle virtual resource sharing and remote cloud, and each subtask can only select one unloading mode.
Step 3.3.1, user self unloading mode: order the
Figure SMS_527
Representing user +.>
Figure SMS_528
Is a subtask->
Figure SMS_529
Completion delay of offloading at user node itself +.>
Figure SMS_530
Can be expressed as:
Figure SMS_531
(5)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_532
representing user +.>
Figure SMS_533
Subtask->
Figure SMS_534
The amount of computation required. Meanwhile, the user uninstalls the computing resource without leasing the computing resource, and the leasing utility of the computing resource is 0.
Step 3.3.2, aerial edge node unloading mode: order the
Figure SMS_536
Representing the total number of edge nodes over the air, +.>
Figure SMS_537
Representation and air edge node->
Figure SMS_538
Is associated with (a) factor(s)>
Figure SMS_539
Representing the air edge node +.>
Figure SMS_540
Assigned to user->
Figure SMS_541
Neutron task->
Figure SMS_542
Is proportional to the computing resource of->
Figure SMS_535
Representing the air edge node +.>
Figure SMS_543
Left computing resources of->
Figure SMS_544
Representing the lease price for the computing resource of the edge node in air. Subtask->
Figure SMS_545
Offloading to an over-the-air edge node->
Figure SMS_546
Is->
Figure SMS_547
Can be expressed as:
Figure SMS_548
(6)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_550
representing user +.>
Figure SMS_552
Subtask->
Figure SMS_554
Transmission data size, +.>
Figure SMS_555
Representing the user +.>
Figure SMS_556
Is of the sub-task of (a)
Figure SMS_557
Uplink transmission to an over-the-air edge node->
Figure SMS_559
Transmission rate of>
Figure SMS_549
Representing user +.>
Figure SMS_551
Subtask->
Figure SMS_553
The amount of computation required. User->
Figure SMS_558
Subtask->
Figure SMS_560
Leasing utility generated by leasing air edge node computing resources>
Figure SMS_561
Expressed as:
Figure SMS_562
(7)；
step 3.3.3, sharing and unloading mode of virtual resources of the vehicle: in addition to considering different idle resources of the vehicle, the user and the vehicle-mounted self-organization are also considered Social trust relationship between fabric networks, let
Figure SMS_564
Representing user and mobile vehicle node->
Figure SMS_565
Trust between dependent on social properties->
Figure SMS_566
Representing a mobile vehicle node +.>
Figure SMS_567
Left computing resources of->
Figure SMS_568
Factor indicating whether or not it is a candidate host vehicle +.>
Figure SMS_569
Factor indicating whether it is an auxiliary shared vehicle, +.>
Figure SMS_570
Representing a vehicle node computing resource lease price. The user node can perceive and comprehensively infer candidate host vehicles and auxiliary shared vehicles through the knowledge graph, dynamically arrange virtual logic resources on the virtual machine to construct a stable shared virtual resource pool, and pool computing resources +.>
Figure SMS_563
Can be expressed as:
Figure SMS_571
(8)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_572
representing auxiliary shared vehicle->
Figure SMS_573
Trust dependent social attributes, +.>
Figure SMS_574
Representing auxiliary shared vehicles
Figure SMS_575
Is a computing resource of (a). Task completion delay for offloading subtasks to vehicle virtual resource sharing +.>
Figure SMS_576
Expressed as:
Figure SMS_577
(9)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_579
representing user +.>
Figure SMS_587
Subtasks of->
Figure SMS_588
Uplink to mobile vehicle node->
Figure SMS_589
Is used for the transmission rate of (a),
Figure SMS_590
representing user +.>
Figure SMS_591
Subtask->
Figure SMS_592
Transmission data size, +.>
Figure SMS_578
Representing user +.>
Figure SMS_580
Type of->
Figure SMS_581
Representing user +.>
Figure SMS_582
Subtask->
Figure SMS_583
The amount of computation required. User->
Figure SMS_584
Subtask->
Figure SMS_585
Rental utility generated by rental vehicle virtual computing resources>
Figure SMS_586
Expressed as:
Figure SMS_593
(10)；/>
step 3.3.4, remote cloud node unloading mode: the cloud can process a plurality of subtasks simultaneously to enable
Figure SMS_596
Representing air edge nodes and users->
Figure SMS_597
Cover factor of->
Figure SMS_598
Representing cloud allocation to users->
Figure SMS_599
Subtask->
Figure SMS_600
Is proportional to the computing resource of->
Figure SMS_601
Representing remaining computing resources of remote cloud node, +.>
Figure SMS_602
Representing time slot->
Figure SMS_594
The remote cloud node calculates a lease price for the resource. Completion delay of subtask offloading to remote cloud node +.>
Figure SMS_595
Expressed as:
Figure SMS_603
(11)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_605
representing ∈k from the air edge node>
Figure SMS_607
Uplink transmission rate to base station, +.>
Figure SMS_608
Representing user +.>
Figure SMS_609
Subtask->
Figure SMS_610
Uplink transmission rate to base station, +.>
Figure SMS_611
Representing the uplink transmission rate between the base station and the cloud. User->
Figure SMS_612
Subtasks
Figure SMS_604
Leasing utility generated by leasing remote cloud computing resources>
Figure SMS_606
Expressed as:
Figure SMS_613
(12)；
step 3.4, construction Contents acquisitionTaking a model; the method comprises the following steps: content acquisition requirements where there may be different access preferences for some users while considering user task offloading, content requirement mobile users can choose to acquire preferred content from vehicle nodes, air edge nodes, and remote cloud nodes, to have
Figure SMS_614
、/>
Figure SMS_615
、/>
Figure SMS_616
Three different acquisition modes are represented, respectively, for the vehicle node, the air edge node, and the remote cloud node.
Step 3.4.1, vehicle node acquisition mode: order the
Figure SMS_618
Representing a mobile vehicle node +.>
Figure SMS_620
Periodically updated existing cached content piece set,/-for >
Figure SMS_621
Rental price indicating that the demand user obtains the desired content from the vehicle node,/->
Figure SMS_622
Representing the user of the demand +.>
Figure SMS_623
And mobile vehicle node->
Figure SMS_624
Downlink transmission rate between the two. Demand user->
Figure SMS_625
From the mobile vehicle node->
Figure SMS_617
Completion delay of acquiring content>
Figure SMS_619
Expressed as:
Figure SMS_626
(13)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_627
representing the user of the demand +.>
Figure SMS_628
The size of the requested content. Rental utility of requiring a user to download vehicle node content>
Figure SMS_629
Expressed as:
Figure SMS_630
(14)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_631
representing the user of the demand +.>
Figure SMS_632
The preference degree of the content is acquired.
Step 3.4.2, air edge node acquisition mode: order the
Figure SMS_634
Representing the air edge node +.>
Figure SMS_636
Part of the existing cached content set,/->
Figure SMS_638
Representing the user's need for content retrieval>
Figure SMS_640
And air edge node->
Figure SMS_642
Is associated with (a) factor(s)>
Figure SMS_643
Lease price indicating that the user is required to acquire content from an over-the-air edge node,/->
Figure SMS_644
Representing the air edge node +.>
Figure SMS_633
Is +.>
Figure SMS_635
Downlink transmission rate between the two. Demand user->
Figure SMS_637
From the air edge node->
Figure SMS_639
Completion delay of acquiring content>
Figure SMS_641
Can be expressed as:
Figure SMS_645
(15)；
rental utility for requiring users to download over-the-air edge node content
Figure SMS_646
Expressed as:
Figure SMS_647
(16)；
step 3.4.3, remote cloud node acquisition mode: order the
Figure SMS_648
Representing time slot->
Figure SMS_649
Requiring the user to obtain the rental price of the content from the remote node, < +.>
Figure SMS_650
And->
Figure SMS_651
Representing cloud node to base station and base station to demand user +. >
Figure SMS_652
Is used for the downlink transmission rate of (a). Demand user->
Figure SMS_653
Completion delay of obtaining content from remote cloud node +.>
Figure SMS_654
Can be expressed as:
Figure SMS_655
(17)；
demand users
Figure SMS_656
Rental utility of downloading remote cloud node content +.>
Figure SMS_657
Expressed as:
Figure SMS_658
(18)；
step 3.5, establishing a system utility function weighted by multiple performance indexes; the specific process is as follows:
step 3.5.1, time slots are allocated by taking into account the different possible offloading modes
Figure SMS_659
Delay and +.>
Figure SMS_660
Expressed as:
Figure SMS_661
(19)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_663
representing subtasks->
Figure SMS_664
Dependency of attribute factor->
Figure SMS_665
Is->
Figure SMS_666
Dependency variable value at attribute time, +.>
Figure SMS_667
Representing the total amount of subtask dependent properties +.>
Figure SMS_668
Representing user +.>
Figure SMS_669
Subtask->
Figure SMS_670
Selecting self-unloading->
Figure SMS_671
Representing subtasks->
Figure SMS_672
Delay in the completion of the self-offloading of the user node +.>
Figure SMS_673
Representing user +.>
Figure SMS_674
Subtask->
Figure SMS_675
Selecting an over-the-air edge nodeThe unloading is carried out by the device,
Figure SMS_676
representing subtasks->Offloading to an over-the-air edge node->
Figure SMS_662
Completion delay of->
Figure SMS_678
Representing user +.>
Figure SMS_679
Subtask->
Figure SMS_680
Selecting vehicle virtual resource sharing offload, +.>
Figure SMS_681
Task completion latency representing offloading of subtasks to vehicle virtual resource sharing +.>
Figure SMS_682
Representing user +.>
Figure SMS_683
Subtask->Selecting remote cloud for task offloading, +.>
Figure SMS_685
Representing the completion latency of the subtask offloading to the remote cloud node.
Step 3.5.2 leasing computing resource leasing utility generated by the edge node
Figure SMS_686
Expressed as:
Figure SMS_687
(20)；/>
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_689
representing user +.>
Figure SMS_691
Subtask->
Figure SMS_692
Leasing the air edge node computing resource generated leasing utility,
Figure SMS_693
representing user +.>
Figure SMS_694
Subtask->
Figure SMS_695
Rental utility generated by rental vehicle virtual computing resources, +.>
Figure SMS_696
Representing user +.>
Figure SMS_688
Subtask->
Figure SMS_690
Leasing a leasing utility generated by a remote cloud computing resource.
Step 3.5.3, combining different content acquisition strategies, requiring the user to be in the time slot
Figure SMS_697
Content acquisition delay and->
Figure SMS_698
The method comprises the following steps:
Figure SMS_699
(21)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_700
representing the user of the demand +.>
Figure SMS_701
Selecting a vehicle node content acquisition mode,/->
Figure SMS_702
Representing the user of the demand +.>
Figure SMS_703
Selecting an over-the-air edge node content acquisition mode, +.>
Figure SMS_704
Representing the user of the demand +.>
Figure SMS_705
A remote cloud node content acquisition mode is selected.
Step 3.5.4, obtaining service lease utility of edge node content by user associated with user demand content size and popularity
Figure SMS_706
Expressed as:
Figure SMS_707
(22)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_708
rental utility indicating that the user is required to download the contents of the vehicle node,/->
Figure SMS_709
Rental utility indicating that the user is required to download the content of the edge node in air,/->
Figure SMS_710
Representing rental utility for requiring the user to download the remote cloud node content.
Step 3.5.5, quantitatively analyzing and calculating a system utility function represented by a weighted sum of unloading and content acquisition time delay, expenditure costs of user leasing edge resources and expenditure costs of content acquisition services
Figure SMS_711
：
Figure SMS_712
(23)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_714
、/>
Figure SMS_715
、/>
Figure SMS_716
、/>
Figure SMS_717
respectively represent time slots->
Figure SMS_719
Delay and +.>
Figure SMS_721
Computing resource lease utility generated by lease edge node>
Figure SMS_723
The demand user is in time slot->
Figure SMS_713
Content acquisition delay and->
Figure SMS_718
Service rental utility of user obtaining edge node content>
Figure SMS_720
Weight coefficient of>
Figure SMS_722
、/>
Figure SMS_724
Representing computing resource lease utility and acquiring edge nodes, respectivelyA discount factor for rental utility of content services.
And 4, constructing an air-ground collaborative unloading and content acquisition optimal strategy based on edge service knowledge graph perception for different types of user demands by adopting a theoretical optimization and clipping near-end strategy optimization algorithm.
Step 4.1, constructing an optimization problem; the method comprises the following steps: minimizing computing offload latency for edge services, content acquisition latency, user leased edge computing resources and leased edge content utility expenditures and achieving the goal of long-term network utility maximization. The original optimization problem established is expressed as
Figure SMS_725
：/>
Figure SMS_726
(24)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_756
represents the maximum number of time slots,/->
Figure SMS_758
Representing the user's need for content retrieval>
Figure SMS_759
And air edge node->
Figure SMS_761
Is a correlation factor of (2); />
Figure SMS_763
Representing user +.>
Figure SMS_764
Subtasks of->
Figure SMS_765
Selecting a user self, an air edge node, vehicle virtual resource sharing and remote cloud node computing unloading mode and requiring users +. >
Figure SMS_766
Selecting three content acquisition modes of a vehicle node, an aerial edge node and a remote cloud node; />
Figure SMS_767
Indicating that a user can only select one mode to perform task unloading and content acquisition; />
Figure SMS_768
Subtask representing user->
Figure SMS_769
When different computing task unloading is selected, only one air edge node and one vehicle node are selected as a host vehicle, and a user is required to be +.>
Figure SMS_770
When content acquisition is carried out through the aerial edge node, only one node is selected; />
Figure SMS_771
Indicating that the distance between the air edge nodes is not less than the minimum safe distance, and the non-preset angle change range is +.>
Figure SMS_772
；/>
Figure SMS_773
Indicating that the mobile positions of the air edge node, the vehicle node and the user do not exceed the set area limit; />
Figure SMS_727
A scale factor representing the allocation of computing resources; />
Figure SMS_730
And
Figure SMS_732
indicating that the distribution of computing resources does not exceed the total computing resources of the user node, the air edge node and the remote cloud node during unloading respectively; />Indicating that the task calculation unloading time delay does not exceed the maximum unloading tolerance time delay, and the user content request time delay is smaller than or equal to the maximum unloading tolerance time delay of the content request; />
Figure SMS_735
Representing the air edge node +.>
Figure SMS_737
And another air edge node->
Figure SMS_739
A distance therebetween; />
Figure SMS_742
Representing a minimum security distance between adjacent air edge nodes; / >
Figure SMS_743
Representing the air edge node +.>
Figure SMS_744
Is a horizontal axis coordinate value; />
Figure SMS_745
Representing user +.>
Figure SMS_747
Is a horizontal axis coordinate value; />
Figure SMS_748
Representing a mobile vehicle node +.>
Figure SMS_750
Is a horizontal axis coordinate value; />
Figure SMS_753
A horizontal axis coordinate value representing the coverage area boundary of the macro base station; />
Figure SMS_754
Representing the air edge node +.>
Figure SMS_728
Is a vertical axis coordinate value of (2); />
Figure SMS_729
Representing user +.>
Figure SMS_731
Is a vertical axis coordinate value of (2); />
Figure SMS_733
Representing a mobile vehicle node +.>
Figure SMS_736
Is a vertical axis coordinate value of (2); />
Figure SMS_738
Representing the vertical axis coordinate value of the coverage area boundary of the macro base station; />
Figure SMS_740
Representing user +.>
Figure SMS_741
Subtasks of->
Figure SMS_746
Is used for unloading calculation time delay; />
Figure SMS_749
Representing user +.>
Figure SMS_751
Subtasks of->
Figure SMS_752
Unloading the maximum tolerant delay; />
Figure SMS_755
Representing the user of the demand +.>
Figure SMS_757
Selecting content acquisition time delay generated by adding different content acquisition modes; />
Figure SMS_760
Representing the user of the demand +.>
Figure SMS_762
The maximum tolerated delay for content retrieval of (c).
Step 4.2, optimizing the solution: first, the original optimization problem
Figure SMS_775
The medium discrete variable relaxes to become a continuous interval variable. Secondly, introducing an upper-limit relaxation variable +.>
Figure SMS_776
Which is converted into a linear term. Definitions->
Figure SMS_777
Representing user +.>
Figure SMS_778
Subtasks of->
Figure SMS_779
Selecting leasing utilities of computing resources generated by adding different unloading modes; />
Figure SMS_780
Representing the user of the demand +.>
Figure SMS_781
Selecting content acquisition time delay generated by adding different content acquisition modes; / >
Figure SMS_774
Representing the user of the demand +.>
Figure SMS_782
The content service rental utilities resulting from the addition of the different content acquisitions are selected. The optimization problem is expressed as follows after simplification>
Figure SMS_783
：
Figure SMS_784
(25)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_786
represents a relaxation of four unloading and three content acquisition discrete variables into a continuous variable between 0 and 1,/v>
Figure SMS_787
Representing the user +.>
Figure SMS_788
The dependency attribute factor in all subtasks is +.>
Figure SMS_789
Upper bound relaxation variable constraint of ∈10->
Figure SMS_790
Representing subtasks->
Figure SMS_791
Dependency of attribute factor->
Figure SMS_792
Is->
Figure SMS_785
The dependency variable value at the time of the attribute,
Figure SMS_793
representing user +.>
Figure SMS_794
The dependency attribute factor in all subtasks is +.>
Figure SMS_795
Upper bound relaxation variable of (2).
Decomposing the optimization problem into three sub-problems, namely the sub-problems of user calculation unloading and content acquisition variables, by a block coordinate descent method and a successive approximation algorithm
Figure SMS_796
Sub-problem of calculating the resource allocation proportion variable ≡>
Figure SMS_797
And the sub-problem of deployment angle variable of the air node->
Figure SMS_798
. The decomposition of a specific sub-problem is represented as follows: />
And 4.2.1, giving a non-preset angle and calculating a resource allocation proportion strategy, and solving an unloading and content acquisition strategy.
Figure SMS_799
(26)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_800
a discount factor representing the utility of a lease of a computing resource, +.>
Figure SMS_801
Representing a discount factor for obtaining the rental utility of the edge node content service.
And 4.2.2, giving task unloading, content acquisition and a non-preset angle strategy, and solving a computing resource allocation proportion strategy. Because no variable coupling relation exists between the distribution of the computing resources and the acquisition of the content, the optimization problem is further simplified to obtain the sub-problem
Figure SMS_802
Still belongs to the problem of co-solution.
Figure SMS_803
(27)；
And 4.2.3, giving task unloading, content acquisition and calculating a resource allocation proportion strategy, and solving an optimal track strategy of the air edge node. Optimization problem with respect to post relaxation
Figure SMS_804
And variable influence analysis, further simplifying the problem into sub-problems with the same solution when solving the trajectory optimization strategy>
Figure SMS_805
。
Figure SMS_806
(28)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_807
representing a non-preset angle +.>
Figure SMS_808
In the range of 0 to->
Figure SMS_809
Between (I)>
Figure SMS_810
Representing the air edge node +.>
Figure SMS_811
And another air edge node->
Figure SMS_812
Distance between->
Figure SMS_813
Not lower than the minimum safe distance.
Finally, a part of optimized variable parameters are given, variable relaxation is carried out by combining Taylor expansion of local points, the non-convex optimization problem is converted into a convex optimization problem, then different sub-problems are solved, and the theoretical optimal boundary solution of the optimization problem is obtained through multiple iteration and set threshold comparison.
Step 4.3, optimizing and perceiving decision analysis under deployment and shared resource pooling based on continuous clipping near-end strategies: first, define
Figure SMS_814
Representing macrosBase station coordinate position->
Figure SMS_815
Representing remaining computing resources of remote cloud node, +.>
Figure SMS_816
Representing a set of cached content pieces in a cloud, defining an initial network state of the system as +.>
Figure SMS_817
：
Figure SMS_818
(29)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_827
representing user +.>
Figure SMS_834
Is (are) moved positions>
Figure SMS_836
Representing user +.>
Figure SMS_838
Is>
Figure SMS_840
Representing user +.>
Figure SMS_842
Transition probability of->
Figure SMS_844
Representing user +.>
Figure SMS_845
Is->
Figure SMS_846
Representing the user of the demand +.>
Figure SMS_847
Is (are) acquired request>
Figure SMS_848
Representing user +.>
Figure SMS_849
Task model with task topology knowledge relationship, +.>
Figure SMS_850
Representing a mobile vehicle node +.>
Figure SMS_852
Is (are) located>
Figure SMS_854
Representing a mobile vehicle node +.>
Figure SMS_820
Is>
Figure SMS_824
Representing a mobile vehicle node +.>
Figure SMS_826
Trust dependent social attributes, +.>
Figure SMS_828
Representing a mobile vehicle node +.>
Figure SMS_829
Left computing resources of->
Figure SMS_830
Representing a mobile vehicle node +.>
Figure SMS_831
Existing cached content piece set,/->
Figure SMS_832
Indicate->
Figure SMS_833
In the airLocation after edge node deployment, +.>
Figure SMS_835
Representing the speed of movement of the edge node in air, +.>
Figure SMS_837
Representing the air edge node +.>
Figure SMS_839
Left computing resources of->
Figure SMS_841
Representing the air edge node +.>
Figure SMS_843
Is provided for the portion of the existing cached content set. Analyzing a plurality of knowledge factors influencing the quality of service performance, arranging the dynamic knowledge relationship to construct an edge service knowledge graph, and obtaining 'preprocessing' knowledge state information expressed as +. >
Figure SMS_851
The method comprises the steps of carrying out a first treatment on the surface of the Second, the complex motion space at each time slot is defined as +.>
Figure SMS_853
Wherein->
Figure SMS_819
Representing user +.>
Figure SMS_821
Subtasks of->
Figure SMS_822
Different offloading policies of->
Figure SMS_823
Representing different content acquisition policies for the requesting user. The set bonus function under each time slot is denoted +.>
Figure SMS_825
。
The overall flow of space-to-ground collaborative offloading and content acquisition under perceived deployment and shared resource pooling based on continuous clipping near-end policy optimization is as follows:
step 4.3.1, constructing an air-ground collaboration unloading and content acquisition model composed of remote cloud, non-preset track air edge nodes, road mobile vehicles and two types of mobile users with different types and different requirements, and initializing parameters;
step 4.3.2, executing a training round, and initializing a training model to obtain an initial state;
step 4.3.3, executing time slot rounds, analyzing a plurality of time-varying parameter relation arrangement of nodes in layers and among layers to construct an edge service knowledge graph, and obtaining knowledge state information;
step 4.3.4, the knowledge server selects an action strategy through a strategy network;
step 4.3.5, the action strategy is put into the environment for execution, and rewards under the current network state, the next network state, the system utility function, the unloading and content acquisition strategy and the stored experience tuples are obtained;
Step 4.3.6, judging whether the parameters of the current strategy network need to be updated, if so, entering another strategy network and evaluating the network to carry out training update, otherwise, continuously executing and updating the network state;
4.3.7, if all time slot training is finished, calculating average network rewards, finishing one training round, and initializing a training model;
and 4.3.8, if the training round is finished, obtaining an average network reward and an optimal service strategy, and outputting the space cooperation unloading and content acquisition scheme as an optimal scheme.
The decision method pseudocode under the perceived deployment and shared resource pooling based on continuous clipping near-end policy optimization is as follows:
1: initializing environmental parameters, experience storage pools and network rewards;
2: initializing parameters in a neural network;
3: for iteration number variable
Figure SMS_855
=1 to->
Figure SMS_856
Execution of->
Figure SMS_857
The iteration times;
4: initializing a training model to obtain an initial network state
Figure SMS_858
；
5: for time slots
Figure SMS_859
=1 to->
Figure SMS_860
Execution of->
Figure SMS_861
Is the maximum time slot number;
6: constructing an edge service knowledge graph to obtain knowledge state information
Figure SMS_862
；
7: policy network selection action space in clipping near-end policy optimization
Figure SMS_863
；
8: performing an action to obtain a bonus function
Figure SMS_864
The next network state;
9: storing the experience tuples to an experience buffer pool;
10： if (
Figure SMS_865
+1) % />
Figure SMS_866
= 0 or +.>
Figure SMS_867
== />
Figure SMS_868
，/>
Figure SMS_869
Is of batch size;
11: continuously cutting a near-end strategy to optimize, learn and update network parameters;
12: assigning the learned updated parameters to the policy network;
13: updating the network state;
14： End for；
15: calculating an average network prize;
16：End for ；
17: until the preset iteration times are executed and reach convergence;
it should be understood that the above description is not intended to limit the invention to the particular embodiments disclosed, but to limit the invention to the particular embodiments disclosed, and that the invention is not limited to the particular embodiments disclosed, but is intended to cover modifications, adaptations, additions and alternatives falling within the spirit and scope of the invention.

Claims (5)

1. The space-ground collaboration unloading and content obtaining method based on knowledge graph perception is characterized by comprising the following steps of:
step 1, constructing an edge vehicle-mounted self-organizing network environment hollow cooperative unloading and content acquisition model consisting of a macro base station, remote cloud, non-preset track aerial edge nodes, road mobile vehicles and two types of mobile users with different types and different requirements in a 5G macro base station coverage lower edge urban environment;
step 2, dynamically arranging and constructing an edge service knowledge graph based on edge node attributes and a plurality of time-varying parameter knowledge relations among nodes;
Step 3, analyzing user service quality influence factors under different service strategies and establishing a multi-performance index weighted system utility function according to node perception deployment and a vehicle-mounted self-organizing network shared resource pooling knowledge model;
in the step 3, the specific process of establishing the system utility function weighted by the multiple performance indexes is as follows:
step 3.1, constructing an air-ground communication model: the method comprises the following steps:
step 3.1.1, calculating the transmission rate of the space-to-ground communication model by using a shannon formula, and respectively calculating the uplink transmission rate and the downlink transmission rate between nodes during space-to-ground communication as follows:
Figure QLYQS_1
(1)；
Figure QLYQS_2
(2)；
wherein, during uplink communication, the node
Figure QLYQS_4
As transmitting node, node->
Figure QLYQS_6
As receiving node->
Figure QLYQS_8
Representing node->
Figure QLYQS_16
To node->
Figure QLYQS_17
Uplink transmission rate of space-to-ground communication, +.>
Figure QLYQS_18
Representing node->
Figure QLYQS_19
To node->
Figure QLYQS_20
Bandwidth resources allocated for upstream communication between the two,
Figure QLYQS_21
representing node->
Figure QLYQS_22
Is set to the transmission power of (a); node ∈during downlink communication>
Figure QLYQS_23
As transmitting node, node->
Figure QLYQS_24
As a receiving node,
Figure QLYQS_25
representing node->
Figure QLYQS_26
To node->
Figure QLYQS_27
Downlink transmission rate of space-to-ground communication, +.>
Figure QLYQS_3
Representing node->
Figure QLYQS_5
To node->
Figure QLYQS_7
Bandwidth resources allocated for downstream communication between +.>
Figure QLYQS_9
Representing node->
Figure QLYQS_10
Is set to the transmission power of (a); />Representing the open spaceAdditive white gaussian noise during inter-communication; / >
Figure QLYQS_12
Representing node->
Figure QLYQS_13
And node->
Figure QLYQS_14
Path loss factor between->
Figure QLYQS_15
The calculation formula is as follows:
Figure QLYQS_28
(3)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_30
representing the carrier frequency +.>
Figure QLYQS_31
Indicating the speed of light +.>
Figure QLYQS_33
Representing node->
Figure QLYQS_35
And node->
Figure QLYQS_36
Distance between->
Figure QLYQS_37
Representing node->
Figure QLYQS_38
And node->
Figure QLYQS_29
Probability of line-of-sight links between +.>
Figure QLYQS_32
And->
Figure QLYQS_34
Respectively representing the environmental loss of the line-of-sight link and the non-line-of-sight link;
step 3.1.2, calculating the transmission rate of the ground communication model by a shannon formula;
the communication transmission rate between the user and the vehicle node virtual edge is calculated as follows:
Figure QLYQS_39
(4)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_41
representing ground emission node->
Figure QLYQS_42
And ground receiving node->
Figure QLYQS_44
Uplink transmission rate between +.>
Figure QLYQS_46
Representing ground emission node->
Figure QLYQS_48
And ground receiving node->
Figure QLYQS_50
Bandwidth resources allocated between, ">
Figure QLYQS_52
Representing ground emission node->
Figure QLYQS_40
Transmit power of>
Figure QLYQS_43
Indicating channel gain, +.>
Figure QLYQS_45
Representing ground emission node->
Figure QLYQS_47
And ground receiving node->
Figure QLYQS_49
Distance between->
Figure QLYQS_51
An additive white gaussian noise representing when a user communicates with a virtual edge of a vehicle node and between vehicle nodes;
step 3.2, constructing a task model; the method comprises the following steps:
based on the full duplex communication technology, the user can simultaneously perform space-ground collaborative task unloading and content acquisition, and the requirements of the user are divided into calculation unloading requirements and content acquisition requirements; exist under each time slot
Figure QLYQS_53
Individual users and each user generates only one application +.>
Figure QLYQS_56
Application->
Figure QLYQS_58
Can be divided into->
Figure QLYQS_60
A subtask with a dependency relationship, defined as an attribute tuple +.>
Figure QLYQS_62
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>
Figure QLYQS_63
Representing user +.>
Figure QLYQS_64
Type of->
Figure QLYQS_54
Representing the size of the transmitted data +.>
Figure QLYQS_55
Representing the required calculation amount +.>
Figure QLYQS_57
Representing the maximum tolerated delay +.>
Figure QLYQS_59
Representing subtask dependency properties,>
Figure QLYQS_61
representing a subtask sequence number;
random presence in ambient users in terms of user content acquisition requests
Figure QLYQS_66
The demand users are all users
Figure QLYQS_68
In (2) generating a content acquisition request per user while generating a computation offload request, will +.>
Figure QLYQS_70
The individual demand user acquisition request is defined as +.>
Figure QLYQS_72
Wherein->
Figure QLYQS_73
Representing the user of the demand +.>
Figure QLYQS_74
Size of requested content->
Figure QLYQS_75
Representing the user of the demand +.>
Figure QLYQS_65
Obtaining the preference degree of the content->
Figure QLYQS_67
Index representing content piece->
Figure QLYQS_69
Representing the user of the demand +.>
Figure QLYQS_71
Obtaining the maximum tolerable time delay of the content;
step 3.3, constructing a calculation model; the method comprises the following steps:
by variable amounts
Figure QLYQS_76
、/>
Figure QLYQS_77
、/>
Figure QLYQS_78
、/>
Figure QLYQS_79
The method comprises the steps of respectively representing four task unloading modes of a user, an aerial edge node, vehicle virtual resource sharing and remote cloud, wherein each subtask can only select one unloading mode;
step 3.3.1, user self unloading mode:
Subtasks
Figure QLYQS_80
Completion delay of offloading at user node itself +.>
Figure QLYQS_81
Expressed as:
Figure QLYQS_82
(5)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_83
representing user +.>
Figure QLYQS_84
Subtask->
Figure QLYQS_85
The amount of calculation required +.>Representing user +.>
Figure QLYQS_87
Is a computing resource of (a); meanwhile, the user uninstalls the leasing resources without leasing the computing resources, and the leasing utility of the computing resources is 0;
step 3.3.2, aerial edge node unloading mode:
subtasks
Figure QLYQS_88
Offloading to an over-the-air edge node->
Figure QLYQS_89
Is->
Figure QLYQS_90
Expressed as:
Figure QLYQS_91
(6)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_107
representing the total number of edge nodes over the air, +.>
Figure QLYQS_108
Representation and air edge node->
Figure QLYQS_109
Is associated with (a) factor(s)>
Figure QLYQS_110
Representing user +.>
Figure QLYQS_111
Subtask->
Figure QLYQS_112
Transmission data size, +.>
Figure QLYQS_113
Representing the user +.>
Figure QLYQS_92
Subtasks of->
Figure QLYQS_93
Uplink transmission to an over-the-air edge node->
Figure QLYQS_95
Transmission rate of>
Figure QLYQS_96
Representing user +.>
Figure QLYQS_97
Subtask->
Figure QLYQS_98
The amount of calculation required +.>
Figure QLYQS_99
Representing the air edge node +.>
Figure QLYQS_100
Assigned to user->
Figure QLYQS_94
Neutron task->
Figure QLYQS_101
Is proportional to the computing resource of->
Figure QLYQS_102
Representing the air edge node +.>
Figure QLYQS_103
Is a residual computing resource of (1); user->
Figure QLYQS_104
Subtask->
Figure QLYQS_105
Leasing utility generated by leasing air edge node computing resources>
Figure QLYQS_106
Expressed as:
Figure QLYQS_114
(7)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_115
representing lease price of computing resources of the aerial edge node;
step 3.3.3, sharing and unloading mode of virtual resources of the vehicle:
in addition to taking into account the different free resources of the vehicle, The social trust relationship between the user and the vehicle-mounted self-organizing network is considered, the user node can perceive and comprehensively infer candidate host vehicles and auxiliary shared vehicles through the knowledge graph, and dynamically arrange virtual logic resources on the virtual machine to construct a stable shared virtual resource pool, and the stable shared virtual resource pool is used for pooling computing resources
Figure QLYQS_116
Expressed as:
Figure QLYQS_117
(8)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_119
representing user and mobile vehicle node->
Figure QLYQS_120
Trust between dependent on social properties->
Figure QLYQS_123
Representing a mobile vehicle node
Figure QLYQS_124
Left computing resources of->
Figure QLYQS_125
Factor indicating whether it is an auxiliary shared vehicle, +.>
Figure QLYQS_126
Representing auxiliary shared vehicles
Figure QLYQS_127
Trust dependent social attributes, +.>
Figure QLYQS_118
Representing auxiliary shared vehicle->
Figure QLYQS_121
Is a computing resource of (a); task completion delay for offloading subtasks to vehicle virtual resource sharing +.>
Figure QLYQS_122
Expressed as:
Figure QLYQS_128
(9)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_139
representing user +.>
Figure QLYQS_140
Type of->
Figure QLYQS_141
Representing the total number of nodes of the mobile vehicle, +.>
Figure QLYQS_142
Factor indicating whether or not it is a candidate host vehicle +.>
Figure QLYQS_143
Representing user +.>
Figure QLYQS_144
Subtasks of->
Figure QLYQS_145
Uplink to mobile vehicle node->
Figure QLYQS_129
Is used for the transmission rate of (a),
Figure QLYQS_131
representing user +.>
Figure QLYQS_133
Subtask->
Figure QLYQS_134
Transmission data size, +.>
Figure QLYQS_135
Representing user +.>
Figure QLYQS_136
Subtask->
Figure QLYQS_137
The amount of calculation required; user->
Figure QLYQS_138
Subtask->
Figure QLYQS_130
Rental utility generated by rental vehicle virtual computing resources>
Figure QLYQS_132
Expressed as:
Figure QLYQS_146
(10)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_147
representing a vehicle node computing resource lease price;
step 3.3.4, remote cloud node unloading mode:
the cloud can process a plurality of subtasks simultaneously, and the completion time delay of the subtasks to be unloaded to the remote cloud node
Figure QLYQS_148
The method comprises the following steps:
Figure QLYQS_149
(11)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_152
representing air edge nodes and users->
Figure QLYQS_153
Cover factor of->
Figure QLYQS_154
Representing the size of the transmitted data +.>
Figure QLYQS_155
Representing ∈k from the air edge node>
Figure QLYQS_156
Uplink transmission rate to base station, +.>
Figure QLYQS_158
Representing user +.>
Figure QLYQS_160
Subtask->
Figure QLYQS_150
Uplink transmission rate to base station, +.>
Figure QLYQS_157
Indicating uplink transmission rate between base station and cloud, < >>
Figure QLYQS_159
Representing cloud allocation to users->
Figure QLYQS_161
Subtasks
Figure QLYQS_162
Is proportional to the computing resource of->
Figure QLYQS_163
Representing remaining computing resources of the remote cloud node; user->
Figure QLYQS_164
Subtask->
Figure QLYQS_165
Leasing utility generated by leasing remote cloud computing resources>
Figure QLYQS_151
Expressed as:
Figure QLYQS_166
(12)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_167
representing time slot->
Figure QLYQS_168
Calculating the lease price of the resource by the remote cloud node;
step 3.4, constructing a content acquisition model; the method comprises the following steps:
content acquisition requirements where there may be different access preferences for some users while considering user task offloading, content requirement mobile users can choose to acquire preferred content from vehicle nodes, air edge nodes, and remote cloud nodes, to have
Figure QLYQS_169
、/>
Figure QLYQS_170
、/>
Figure QLYQS_171
Three different acquisition modes of a vehicle node, an air edge node and a remote cloud node are respectively represented;
Step 3.4.1, vehicle node acquisition mode:
demand users
Figure QLYQS_172
From the mobile vehicle node->
Figure QLYQS_173
Completion delay of acquiring content>
Figure QLYQS_174
Expressed as:
Figure QLYQS_175
(13)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_176
representing the user of the demand +.>
Figure QLYQS_177
Size of requested content->
Figure QLYQS_178
Representing the user of the demand +.>
Figure QLYQS_179
And mobile vehicle node->
Figure QLYQS_180
Downlink transmission rate between the two; rental utility of requiring a user to download vehicle node content>
Figure QLYQS_181
Expressed as:
Figure QLYQS_182
(14)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_183
rental price indicating that the demand user obtains the desired content from the vehicle node,/->
Figure QLYQS_184
Representing the user of the demand +.>
Figure QLYQS_185
Acquiring the preference degree of the content;
step 3.4.2, air edge node acquisition mode:
demand users
Figure QLYQS_186
From the air edge node->
Figure QLYQS_187
Completion delay of acquiring content>
Figure QLYQS_188
Expressed as:
Figure QLYQS_189
(15)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_190
representing the user's need for content retrieval>
Figure QLYQS_191
And air edge node->
Figure QLYQS_192
Is associated with (a) factor(s)>
Figure QLYQS_193
Representing the air edge node +.>
Figure QLYQS_194
Is +.>
Figure QLYQS_195
Downlink transmission rate between the two; rental utility of requiring users to download over-the-air edge node content>
Figure QLYQS_196
Expressed as:
Figure QLYQS_197
(16)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_198
representing lease unit price for requiring a user to acquire content from an aerial edge node;
step 3.4.3, remote cloud node acquisition mode:
demand users
Figure QLYQS_199
Completion delay of obtaining content from remote cloud node +.>
Figure QLYQS_200
Expressed as:
Figure QLYQS_201
(17)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_202
and->
Figure QLYQS_203
Representing cloud node to base station and base station to demand user +. >
Figure QLYQS_204
Is a downlink transmission rate of (a); for demand useHouse->
Figure QLYQS_205
Rental utility of downloading remote cloud node content +.>
Figure QLYQS_206
Expressed as:
Figure QLYQS_207
(18)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_208
representing time slot->
Figure QLYQS_209
Requiring the user to acquire the lease price of the content from the remote node;
step 3.5, establishing a system utility function weighted by multiple performance indexes; the specific process is as follows:
step 3.5.1, time slots are allocated by taking into account the different possible offloading modes
Figure QLYQS_210
Delay and +.>
Figure QLYQS_211
Expressed as:
Figure QLYQS_212
(19)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_214
representing subtasks->
Figure QLYQS_216
Dependency of attribute factor->
Figure QLYQS_218
Is->
Figure QLYQS_219
Dependency variable value at attribute time, +.>
Figure QLYQS_222
Representing the total amount of subtask dependent properties +.>
Figure QLYQS_227
Representing user +.>
Figure QLYQS_228
Subtask->
Figure QLYQS_229
Selecting self-unloading->
Figure QLYQS_230
Representing subtasks->
Figure QLYQS_231
Delay in the completion of the self-offloading of the user node +.>
Figure QLYQS_232
Representing user +.>
Figure QLYQS_233
Subtask->
Figure QLYQS_234
Selecting over-the-air edge node offload,>
Figure QLYQS_235
representing subtasks->
Figure QLYQS_236
Offloading to an over-the-air edge node->
Figure QLYQS_213
Completion delay of->
Figure QLYQS_215
Representing user +.>
Figure QLYQS_217
Subtask->
Figure QLYQS_220
Selecting vehicle virtual resource sharing offload, +.>
Figure QLYQS_221
Task completion latency representing offloading of subtasks to vehicle virtual resource sharing +.>
Figure QLYQS_223
Representing user +.>
Figure QLYQS_224
Subtask->
Figure QLYQS_225
Selecting remote cloud for task offloading, +.>
Figure QLYQS_226
Representing the completion time delay of the subtask offloading to the remote cloud node;
step 3.5.2 leasing computing resource leasing utility generated by the edge node
Figure QLYQS_237
Expressed as:
Figure QLYQS_238
(20)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_240
representing user +.>
Figure QLYQS_242
Subtask->
Figure QLYQS_243
Leasing the air edge node computing resource generated leasing utility,
Figure QLYQS_244
representing user +.>
Figure QLYQS_245
Subtask->
Figure QLYQS_246
Rental utility generated by rental vehicle virtual computing resources, +.>
Figure QLYQS_247
Representing user +.>
Figure QLYQS_239
Subtask->
Figure QLYQS_241
Leasing the leasing utility generated by the remote cloud computing resource;
step 3.5.3, combining different content acquisition strategies, requiring the user to be in the time slot
Figure QLYQS_248
Content acquisition delay and->
Figure QLYQS_249
Expressed as:
Figure QLYQS_250
(21)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_251
for indicating demandHouse->
Figure QLYQS_252
Selecting a vehicle node content acquisition mode,/->
Figure QLYQS_253
Representing the user of the demand +.>
Figure QLYQS_254
Selecting an over-the-air edge node content acquisition mode, +.>
Figure QLYQS_255
Representing the user of the demand +.>
Figure QLYQS_256
Selecting a remote cloud node content acquisition mode;
step 3.5.4, obtaining service lease utility of edge node content by user associated with user demand content size and popularity
Figure QLYQS_257
Expressed as:
Figure QLYQS_258
(22)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_259
rental utility indicating that the user is required to download the contents of the vehicle node,/->
Figure QLYQS_260
Rental utility indicating that the user is required to download the content of the edge node in air,/->
Figure QLYQS_261
Representing leasing utility of a demand user to download remote cloud node content;
step 3.5.5, quantitatively analyzing, calculating and unloading and obtaining time delay of contentSystem utility function for weighted sum representation of payout rental utility of user rental edge resources and payout rental utility of content acquisition service
Figure QLYQS_262
：
Figure QLYQS_263
(23)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_269
、/>
Figure QLYQS_270
、/>
Figure QLYQS_271
、/>
Figure QLYQS_272
respectively represent time slots->
Figure QLYQS_273
Delay and +.>
Figure QLYQS_274
Computing resource lease utility generated by lease edge node>
Figure QLYQS_275
The demand user is in time slot->
Figure QLYQS_264
Content acquisition delay and->
Figure QLYQS_265
Service rental utility of user obtaining edge node content>
Figure QLYQS_266
Weight coefficient of>
Figure QLYQS_267
、/>
Figure QLYQS_268
Respectively representing computing resource lease utility and obtaining discount factors of edge node content service lease utility;
and 4, constructing an air-ground collaborative unloading and content acquisition optimal strategy based on edge service knowledge graph perception for different types of user demands by adopting a theoretical optimization and clipping near-end strategy optimization algorithm.
2. The method for air-ground collaboration offloading and content acquisition based on knowledge-graph perception according to claim 1, wherein in the step 1, an edge city air-ground collaboration scene in which a 5G macro base station covers remote clouds, air edge nodes, road moving vehicles and two types of mobile users with different types and different requirements coexist is considered; the macro base station is provided with an edge knowledge server for knowledge spectrum sensing, senses physical entity information of users, vehicles and aerial edge nodes in a coverage area, is connected with a remote cloud in an optical fiber communication mode, and contains a large amount of computing resources and cache content fragment sets; meanwhile, quantitatively labeling the positions of different physical entities in the scene by establishing a three-dimensional coordinate system; the unmanned aerial vehicle with fixed height flies at a non-preset angle to be used as an air edge node for flexible perception decision deployment, a minimum safety distance is set between adjacent air edge nodes, and the air edge node contains computing resources and part of the existing cache content set updated periodically so as to assist a user to carry out task unloading, relay forwarding and cache content providing, wherein the air edge node and a macro base station communicate through an air link; two kinds of task users with different moving speeds and tolerant time delays exist in the scene, namely a common user and a vehicle-mounted user; a plurality of moving vehicle nodes exist on the surrounding roads of the cell, each vehicle node carries a virtual machine capable of carrying out logic resource migration and an existing cache content fragment set of the vehicle node which is updated periodically, and the virtual machine has vehicle residual computing resources with heterogeneous different sizes and trust dependence social attributes between users and the vehicle nodes; a small number of non-trusted vehicles exist, the vehicles are divided into a host vehicle and auxiliary shared vehicles sharing resources in the edge service process, communication availability ranges exist among different vehicle nodes and among vehicle nodes and task users, and the users communicate with the aerial edge nodes, the vehicle nodes and the host vehicle and the auxiliary shared vehicles through wireless communication links; the air edge node and the vehicle node also serve as edge cache nodes to provide content for users with content acquisition requirements.
3. The space-to-ground collaboration unloading and content acquisition method based on knowledge graph perception according to claim 1, wherein in the step 2, the specific process of constructing the edge service knowledge graph is as follows:
step 2.1, abstracting the air-ground collaboration unloading and content acquisition model network entity constructed in the step 1 into nodes and establishing different logic layers, namely a program task layer, a user layer, a vehicle node layer, an air edge node layer and a cloud node layer;
step 2.2, extracting and analyzing characteristic knowledge of nodes in each layer, and extracting multi-time-varying parameter knowledge relations among the nodes in the layers;
step 2.3, node attribute embedding is carried out on the intra-layer nodes, time-varying parameter knowledge relation arrangement among the nodes is carried out to construct edge relations and parameter weight factors, and multi-time-varying parameter relation arrangement is carried out on the inter-layer nodes according to different edge relation criteria to construct inter-layer node knowledge relations and parameter weight factors;
step 2.4, establishing an undirected weighted graph to obtain an edge service knowledge graph; the method comprises the following steps: the edge service knowledge graph is obtained through dynamic arrangement of different side relation criteria on multi-time-varying parameter knowledge relations and is expressed as an undirected weighted graph
Figure QLYQS_276
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1) >
Figure QLYQS_277
Representing node set,/->
Figure QLYQS_278
Representing edges in the undirected weighted graph, +.>
Figure QLYQS_279
Representing the embedded parametric weight.
4. The space-to-ground collaboration unloading and content acquisition method based on knowledge-graph perception according to claim 1, wherein in the step 4, the specific process of acquiring the optimal strategy is as follows:
step 4.1, constructing an optimization problem; the method comprises the following steps:
minimizing computing unloading delay, content acquisition delay of edge service, leasing edge computing resources by users and leasing edge content utility expenditure and achieving the goal of maximizing long-term network utility; the original optimization problem established is expressed as
Figure QLYQS_280
：
Figure QLYQS_281
(24)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_282
represents the maximum number of time slots,/->
Figure QLYQS_284
Representing a non-preset angle; />
Figure QLYQS_286
Representing user +.>
Figure QLYQS_288
Subtasks of->
Figure QLYQS_290
Selecting a user self, an air edge node, vehicle virtual resource sharing and remote cloud node computing unloading mode and requiring users +.>
Figure QLYQS_292
Selecting three content acquisition modes of a vehicle node, an aerial edge node and a remote cloud node; />
Figure QLYQS_294
Indicating that a user can only select one mode to perform task unloading and content acquisition; />
Figure QLYQS_297
Subtask representing user->
Figure QLYQS_302
When different computing task unloading is selected, only one air edge node and one vehicle node are selected as a host vehicle, and a user is required to be +. >
Figure QLYQS_304
When content acquisition is carried out through the aerial edge node, only one node is selected; />
Figure QLYQS_306
Indicating that the distance between the air edge nodes is not less than the minimum safe distance, and the non-preset angle change range is +.>
Figure QLYQS_307
；/>
Figure QLYQS_309
Indicating that the mobile positions of the air edge node, the vehicle node and the user do not exceed the set area limit;
Figure QLYQS_311
a scale factor representing the allocation of computing resources; />
Figure QLYQS_313
And->
Figure QLYQS_314
Indicating that the distribution of computing resources does not exceed the total computing resources of the user node, the air edge node and the remote cloud node during unloading respectively; />
Figure QLYQS_315
Indicating that the task calculation unloading time delay does not exceed the maximum unloading tolerance time delay, and the user content request time delay is smaller than or equal to the maximum unloading tolerance time delay of the content request; />
Figure QLYQS_316
Representing the user's need for content retrieval>
Figure QLYQS_317
And air edge node->
Figure QLYQS_318
Is a correlation factor of (2); />
Figure QLYQS_319
Representing the air edge node +.>
Figure QLYQS_320
And another air edge node->
Figure QLYQS_321
A distance therebetween; />
Figure QLYQS_322
Representing a minimum security distance between adjacent air edge nodes; />
Figure QLYQS_323
Representing the air edge node +.>
Figure QLYQS_324
Is a horizontal axis coordinate value; />
Figure QLYQS_325
Representing user +.>
Figure QLYQS_326
Is a horizontal axis coordinate value; />
Figure QLYQS_327
Representing a mobile vehicle node +.>
Figure QLYQS_328
Is a horizontal axis coordinate value; />
Figure QLYQS_329
A horizontal axis coordinate value representing the coverage area boundary of the macro base station; />
Figure QLYQS_283
Representing the air edge node +.>
Figure QLYQS_285
Is a vertical axis coordinate value of (2);
Figure QLYQS_287
Representing user +.>
Figure QLYQS_289
Is a vertical axis coordinate value of (2); />
Figure QLYQS_291
Representing a mobile vehicle node +.>
Figure QLYQS_293
Is a vertical axis coordinate value of (2); />
Figure QLYQS_295
Representing the vertical axis coordinate value of the coverage area boundary of the macro base station; />
Figure QLYQS_296
Representing user +.>
Figure QLYQS_298
Subtasks of->
Figure QLYQS_299
Is used for unloading calculation time delay; />
Figure QLYQS_300
Representing user +.>
Figure QLYQS_301
Subtasks of->
Figure QLYQS_303
Unloading the maximum tolerant delay; />
Figure QLYQS_305
Representing the user of the demand +.>
Figure QLYQS_308
Selecting content acquisition time delay generated by adding different content acquisition modes; />
Figure QLYQS_310
Representing the user of the demand +.>
Figure QLYQS_312
Maximum tolerant time delay of content acquisition;
step 4.2, optimizing the solution: first, the original optimization problem
Figure QLYQS_330
The medium discrete variable is relaxed to be changed into a continuous interval variable; second, introducing an upper-bound relaxation variable to the maximum nonlinear term in the objective function>
Figure QLYQS_331
It is subjected toConverting into linear term and adding new constraint condition +.>
Figure QLYQS_332
Optimization problem after relaxation->
Figure QLYQS_333
Is->
Figure QLYQS_334
Performing an equivalent solution; the optimization problem is expressed as follows after simplification>
Figure QLYQS_335
：
Figure QLYQS_336
(25)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_347
representing user +.>
Figure QLYQS_349
Subtasks of->
Figure QLYQS_350
Selecting leasing utilities of computing resources generated by adding different unloading modes;
Figure QLYQS_351
representing the user of the demand +.>
Figure QLYQS_352
Selecting content acquisition time delay generated by adding different content acquisition modes; />
Figure QLYQS_353
Representing the user of the demand +.>
Figure QLYQS_354
Selecting a content service lease utility generated by adding different content acquisitions; />
Figure QLYQS_337
Represents a relaxation of four unloading and three content acquisition discrete variables into a continuous variable between 0 and 1,/v >
Figure QLYQS_339
Representing the user +.>
Figure QLYQS_341
The dependency attribute factor in all subtasks is +.>
Figure QLYQS_342
Upper bound relaxation variable constraint of ∈10->
Figure QLYQS_343
Representing subtasks->
Figure QLYQS_344
Dependency of attribute factor->
Figure QLYQS_345
Is->
Figure QLYQS_346
Dependency variable value at attribute time, +.>
Figure QLYQS_338
Representing user +.>
Figure QLYQS_340
The dependency attribute factor in all subtasks is +.>
Figure QLYQS_348
Upper limit relaxation variable of (2);
the optimization problem is decomposed into three sub-components by a block coordinate descent method and a successive approximation algorithmProblems: user computing offload and content acquisition variable sub-questions
Figure QLYQS_355
Sub-problem of calculating the resource allocation proportion variable ≡>
Figure QLYQS_356
And the sub-problem of deployment angle variable of the air node->
Figure QLYQS_357
The method comprises the steps of carrying out a first treatment on the surface of the The decomposition of a specific sub-problem is represented as follows:
step 4.2.1, giving a non-preset angle and calculating a resource allocation proportion strategy, and solving an unloading and content acquisition strategy;
Figure QLYQS_358
(26)；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_359
a discount factor representing the utility of a lease of a computing resource, +.>
Figure QLYQS_360
Representing a discount factor for obtaining the lease utility of the edge node content service;
step 4.2.2, given task unloading, content acquisition and non-preset angle strategies, solving a calculation resource allocation proportion strategy;
because no variable coupling relation exists between the distribution of the computing resources and the acquisition of the content, the optimization problem is further simplified to obtain the sub-problem
Figure QLYQS_361
Still belonging to the same solution problem;
Figure QLYQS_362
(27)；
step 4.2.3, giving task unloading, content acquisition and calculating a resource allocation proportion strategy, and solving an optimal track strategy of the aerial edge node;
optimization problem with respect to post relaxation
Figure QLYQS_363
And variable influence analysis, further simplifying the problem into sub-problems with the same solution when solving the trajectory optimization strategy>
Figure QLYQS_364
；
Figure QLYQS_365
(28)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_366
representing a non-preset angle +.>
Figure QLYQS_367
In the range of 0 to->
Figure QLYQS_368
Between (I)>
Figure QLYQS_369
Representing the air edge node +.>
Figure QLYQS_370
And another air edge node->
Figure QLYQS_371
Distance between->
Figure QLYQS_372
Not lower than the minimum safe distance;
finally, a part of optimized variable parameters are given, variable relaxation is carried out by combining Taylor expansion of local points, the non-convex optimization problem is converted into a convex optimization problem, then different sub-problems are solved, and a theoretical optimal boundary solution of the optimization problem is obtained through multiple iteration and set threshold comparison;
step 4.3, optimizing and perceiving decision analysis under deployment and shared resource pooling based on continuous clipping near-end strategies:
first, define the initial network state of the system as
Figure QLYQS_373
：
Figure QLYQS_374
(29)；
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure QLYQS_378
representing user +.>
Figure QLYQS_380
Is (are) moved positions>
Figure QLYQS_382
Representing user +.>
Figure QLYQS_384
Is>
Figure QLYQS_386
Representing user +.>
Figure QLYQS_391
Transition probability of->
Figure QLYQS_392
Representing user +.>
Figure QLYQS_394
Is- >
Figure QLYQS_396
Representing the user of the demand +.>
Figure QLYQS_398
Is (are) acquired request>
Figure QLYQS_402
Representing user +.>
Figure QLYQS_403
Task model with task topology knowledge relationship, +.>
Figure QLYQS_404
Representing a mobile vehicle node +.>
Figure QLYQS_405
Is (are) located>
Figure QLYQS_406
Representing a mobile vehicle node +.>
Figure QLYQS_375
Is>
Figure QLYQS_377
Representing a mobile vehicle node +.>
Figure QLYQS_379
Trust dependent social attributes, +.>
Figure QLYQS_381
Representing a mobile vehicle node +.>
Figure QLYQS_383
Left computing resources of->
Figure QLYQS_385
Representing a mobile vehicle node +.>
Figure QLYQS_387
Existing cached content piece set,/->
Figure QLYQS_388
Indicate->
Figure QLYQS_389
Post-deployment location of individual air edge nodes, +.>
Figure QLYQS_390
Representing the speed of movement of the edge node in air, +.>
Figure QLYQS_393
Representing the air edge node +.>
Figure QLYQS_395
Left computing resources of->
Figure QLYQS_397
Representing the air edge node +.>
Figure QLYQS_399
Part of the existing cached content set,/->
Figure QLYQS_400
Indicating macro base station coordinate position,/->
Figure QLYQS_401
Representing remaining computing resources of remote cloud node, +.>
Figure QLYQS_376
Representing a cached content segment set in the cloud;
analyzing a plurality of knowledge factors influencing the service quality performance, arranging the dynamic knowledge relationship to construct an edge service knowledge graph, and expressing the obtained preprocessing knowledge state information as
Figure QLYQS_407
；
Second, define the complex motion space under each time slot as
Figure QLYQS_408
Wherein, the method comprises the steps of, wherein,
Figure QLYQS_409
representing user +.>
Figure QLYQS_410
Subtasks of->
Figure QLYQS_411
Different offloading policies of->
Figure QLYQS_412
Representing different content acquisition strategies of a demand user; the set bonus function under each time slot is denoted +. >
Figure QLYQS_413
。
5. The method for air-ground collaborative offloading and content acquisition based on knowledge-graph perception according to claim 4, wherein in step 4.3, the overall flow of the air-ground collaborative offloading and content acquisition based on perceived deployment and shared resource pooling optimized by continuous clipping near-end policy is as follows:
step 4.3.1, constructing an air-ground collaboration unloading and content acquisition model composed of remote cloud, non-preset track air edge nodes, road mobile vehicles and two types of mobile users with different types and different requirements, and initializing parameters;
step 4.3.2, executing a training round, and initializing a training model to obtain an initial state;
step 4.3.3, executing time slot rounds, analyzing a plurality of time-varying parameter relation arrangement of nodes in layers and among layers to construct an edge service knowledge graph, and obtaining knowledge state information;
step 4.3.4, the knowledge server selects an action strategy through a strategy network;
step 4.3.5, the action strategy is put into the environment for execution, and rewards under the current network state, the next network state, the system utility function, the unloading and content acquisition strategy and the stored experience tuples are obtained;
step 4.3.6, judging whether the parameters of the current strategy network need to be updated, if so, entering another strategy network and evaluating the network to carry out training update, otherwise, continuously executing and updating the network state;
4.3.7, if all time slot training is finished, calculating average network rewards, finishing one training round, and initializing a training model;
and 4.3.8, if the training round is finished, obtaining an average network reward and an optimal service strategy, and outputting the space cooperation unloading and content acquisition scheme as an optimal scheme.
CN202310408910.2A 2023-04-18 2023-04-18 Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception Active CN116208970B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310408910.2A CN116208970B (en) 2023-04-18 2023-04-18 Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310408910.2A CN116208970B (en) 2023-04-18 2023-04-18 Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception

Publications (2)

Publication Number Publication Date
CN116208970A CN116208970A (en) 2023-06-02
CN116208970B true CN116208970B (en) 2023-07-14

Family

ID=86514890

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310408910.2A Active CN116208970B (en) 2023-04-18 2023-04-18 Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception

Country Status (1)

Country Link
CN (1) CN116208970B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111913723A (en) * 2020-06-15 2020-11-10 合肥工业大学 Cloud-edge-end cooperative unloading method and system based on assembly line
CN112800247A (en) * 2021-04-09 2021-05-14 华中科技大学 Semantic encoding/decoding method, equipment and communication system based on knowledge graph sharing
WO2021233053A1 (en) * 2020-05-22 2021-11-25 华为技术有限公司 Computing offloading method and communication apparatus
WO2022121559A1 (en) * 2020-12-07 2022-06-16 中兴通讯股份有限公司 Mobile communication system control method, network management and control agent, system, and storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112732718B (en) * 2021-01-06 2022-06-14 华南理工大学 Intelligent structured data method, system and medium for cloud side
CN114915629B (en) * 2021-02-10 2023-08-15 中国移动通信有限公司研究院 Information processing method, device, system, electronic equipment and storage medium
CN113742046A (en) * 2021-09-17 2021-12-03 苏州大学 Flow grooming cloud-side computing network computing resource balanced scheduling method and system
CN115129888A (en) * 2022-06-14 2022-09-30 大连理工大学 Active content caching method based on network edge knowledge graph
CN115243217B (en) * 2022-07-07 2023-07-18 中山大学 DDQN-based terminal Bian Yun cooperative scheduling method and system in Internet of vehicles edge environment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021233053A1 (en) * 2020-05-22 2021-11-25 华为技术有限公司 Computing offloading method and communication apparatus
CN111913723A (en) * 2020-06-15 2020-11-10 合肥工业大学 Cloud-edge-end cooperative unloading method and system based on assembly line
WO2022121559A1 (en) * 2020-12-07 2022-06-16 中兴通讯股份有限公司 Mobile communication system control method, network management and control agent, system, and storage medium
CN112800247A (en) * 2021-04-09 2021-05-14 华中科技大学 Semantic encoding/decoding method, equipment and communication system based on knowledge graph sharing

Also Published As

Publication number Publication date
CN116208970A (en) 2023-06-02

Similar Documents

Publication Publication Date Title
Hu et al. Twin-timescale artificial intelligence aided mobility-aware edge caching and computing in vehicular networks
CN113282368B (en) Edge computing resource scheduling method for substation inspection
Chen et al. Multiuser computation offloading and resource allocation for cloud–edge heterogeneous network
Wu et al. Deep reinforcement learning-based computation offloading for 5G vehicle-aware multi-access edge computing network
CN111182495B (en) 5G internet of vehicles partial calculation unloading method
CN111132191A (en) Method for unloading, caching and resource allocation of joint tasks of mobile edge computing server
CN112512065B (en) Method for unloading and migrating under mobile awareness in small cell network supporting MEC
Wang et al. Q‐learning based computation offloading for multi‐UAV‐enabled cloud‐edge computing networks
Lin et al. Deep reinforcement learning-based task scheduling and resource allocation for NOMA-MEC in Industrial Internet of Things
CN114698128A (en) Anti-interference channel selection method and system for cognitive satellite-ground network
Tan et al. Resource allocation of fog radio access network based on deep reinforcement learning
Li et al. Multi-task offloading scheme for UAV-enabled fog computing networks
Hu et al. Deep reinforcement learning for task offloading in edge computing assisted power IoT
Tefera et al. Congestion‐aware adaptive decentralised computation offloading and caching for multi‐access edge computing networks
KR101924628B1 (en) Apparatus and Method for controlling traffic offloading
Li et al. Collaborative optimization of edge-cloud computation offloading in internet of vehicles
CN116208970B (en) Air-ground collaboration unloading and content acquisition method based on knowledge-graph perception
CN115361453B (en) Load fair unloading and migration method for edge service network
Zhu et al. Computing offloading decision based on multi-objective immune algorithm in mobile edge computing scenario
CN114615730B (en) Power distribution method for content coverage of backhaul-limited dense wireless network
CN116321293A (en) Edge computing unloading and resource allocation method based on multi-agent reinforcement learning
CN115766478A (en) Unloading method of air-ground cooperative edge computing server
Lei et al. Partially collaborative edge caching based on federated deep reinforcement learning
CN115052262A (en) Potential game-based vehicle networking computing unloading and power optimization method
CN114626298A (en) State updating method for efficient caching and task unloading in unmanned aerial vehicle-assisted Internet of vehicles

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant